diff --git a/Cargo.lock b/Cargo.lock
index 915de0d582e..547cff9b78f 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -24,7 +24,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e89da841a80418a9b391ebaea17f5c112ffaaa96f621d2c285b5174da76b9011"
 dependencies = [
  "cfg-if",
- "getrandom",
+ "getrandom 0.2.15",
  "once_cell",
  "serde",
  "version_check",
@@ -48,9 +48,9 @@ checksum = "4aa90d7ce82d4be67b64039a3d588d38dbcc6736577de4a847025ce5b0c468d1"
 
 [[package]]
 name = "allocator-api2"
-version = "0.2.20"
+version = "0.2.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "45862d1c77f2228b9e10bc609d5bc203d86ebc9b87ad8d5d5167a6c9abf739d9"
+checksum = "683d7910e743518b0e34f1186f92494becacb047c7b6bf616c96772180fef923"
 
 [[package]]
 name = "android-tzdata"
@@ -108,19 +108,20 @@ dependencies = [
 
 [[package]]
 name = "anstyle-wincon"
-version = "3.0.6"
+version = "3.0.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2109dbce0e72be3ec00bed26e6a7479ca384ad226efdd66db8fa2e3a38c83125"
+checksum = "ca3534e77181a9cc07539ad51f2141fe32f6c3ffd4df76db8ad92346b003ae4e"
 dependencies = [
  "anstyle",
+ "once_cell",
  "windows-sys 0.59.0",
 ]
 
 [[package]]
 name = "anyhow"
-version = "1.0.93"
+version = "1.0.95"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4c95c10ba0b00a02636238b814946408b1322d5ac4760326e6fb8ec956d85775"
+checksum = "34ac096ce696dc2fcabef30516bb13c0a68a11d30131d3df6f04711467681b04"
 
 [[package]]
 name = "arbitrary"
@@ -142,7 +143,7 @@ checksum = "0ae92a5119aa49cdbcf6b9f893fe4e1d98b04ccbf82ee0584ad948a44a734dea"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -181,18 +182,18 @@ checksum = "c7c24de15d275a1ecfd47a380fb4d5ec9bfe0933f309ed5e705b775596a3574d"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
 name = "async-trait"
-version = "0.1.83"
+version = "0.1.85"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "721cae7de5c34fbb2acd27e21e6d2cf7b886dce0c27388d46c4e6c47ea4318dd"
+checksum = "3f934833b4b7233644e5848f235df3f57ed8c80f1528a26c3dfa13d2147fa056"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -266,28 +267,26 @@ dependencies = [
 
 [[package]]
 name = "aws-lc-rs"
-version = "1.11.0"
+version = "1.12.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fe7c2840b66236045acd2607d5866e274380afd87ef99d6226e961e2cb47df45"
+checksum = "4c2b7ddaa2c56a367ad27a094ad8ef4faacf8a617c2575acb2ba88949df999ca"
 dependencies = [
  "aws-lc-sys",
- "mirai-annotations",
  "paste",
  "zeroize",
 ]
 
 [[package]]
 name = "aws-lc-sys"
-version = "0.23.0"
+version = "0.25.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ad3a619a9de81e1d7de1f1186dcba4506ed661a0e483d84410fdef0ee87b2f96"
+checksum = "71b2ddd3ada61a305e1d8bb6c005d1eaa7d14d903681edfc400406d523a9b491"
 dependencies = [
- "bindgen",
+ "bindgen 0.69.5",
  "cc",
  "cmake",
  "dunce",
  "fs_extra",
- "libc",
  "paste",
 ]
 
@@ -304,7 +303,7 @@ dependencies = [
  "futures-util",
  "http 0.2.12",
  "http-body 0.4.6",
- "hyper 0.14.31",
+ "hyper 0.14.32",
  "itoa",
  "matchit",
  "memchr",
@@ -333,10 +332,10 @@ dependencies = [
  "axum-core 0.4.5",
  "bytes",
  "futures-util",
- "http 1.1.0",
+ "http 1.2.0",
  "http-body 1.0.1",
  "http-body-util",
- "hyper 1.5.1",
+ "hyper 1.6.0",
  "hyper-util",
  "itoa",
  "matchit",
@@ -351,7 +350,7 @@ dependencies = [
  "serde_urlencoded",
  "sync_wrapper 1.0.2",
  "tokio",
- "tower 0.5.1",
+ "tower 0.5.2",
  "tower-layer",
  "tower-service",
  "tracing",
@@ -383,7 +382,7 @@ dependencies = [
  "async-trait",
  "bytes",
  "futures-util",
- "http 1.1.0",
+ "http 1.2.0",
  "http-body 1.0.1",
  "http-body-util",
  "mime",
@@ -404,7 +403,7 @@ dependencies = [
  "axum 0.7.9",
  "futures-core",
  "futures-util",
- "http 1.1.0",
+ "http 1.2.0",
  "opentelemetry 0.21.0",
  "pin-project-lite",
  "tower 0.4.13",
@@ -452,7 +451,7 @@ version = "0.69.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "271383c67ccabffb7381723dea0672a673f292304fcb45c01cc648c7a8d58088"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.8.0",
  "cexpr",
  "clang-sys",
  "itertools 0.12.1",
@@ -463,12 +462,32 @@ dependencies = [
  "proc-macro2",
  "quote",
  "regex",
- "rustc-hash",
+ "rustc-hash 1.1.0",
  "shlex",
- "syn 2.0.89",
+ "syn 2.0.96",
  "which",
 ]
 
+[[package]]
+name = "bindgen"
+version = "0.71.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5f58bf3d7db68cfbac37cfc485a8d711e87e064c3d0fe0435b92f7a407f9d6b3"
+dependencies = [
+ "bitflags 2.8.0",
+ "cexpr",
+ "clang-sys",
+ "itertools 0.13.0",
+ "log",
+ "prettyplease",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "rustc-hash 2.1.0",
+ "shlex",
+ "syn 2.0.96",
+]
+
 [[package]]
 name = "bit-set"
 version = "0.8.0"
@@ -498,9 +517,9 @@ checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
 
 [[package]]
 name = "bitflags"
-version = "2.6.0"
+version = "2.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b048fb63fd8b5923fc5aa7b340d8e156aec7ec02f0c78fa8a6ddc2613f6f71de"
+checksum = "8f68f53c83ab957f72c32642f3868eec03eb974d1fb82e453128456482613d36"
 
 [[package]]
 name = "bitstream-io"
@@ -531,9 +550,9 @@ checksum = "c360505aed52b7ec96a3636c3f039d99103c37d1d9b4f7a8c743d3ea9ffcd03b"
 
 [[package]]
 name = "bumpalo"
-version = "3.16.0"
+version = "3.17.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "79296716171880943b8470b5f8d03aa55eb2e645a4874bdbb28adb49162e012c"
+checksum = "1628fb46dfa0b37568d12e5edd512553eccf6a22a78e8bde00bb4aed84d5bdbf"
 
 [[package]]
 name = "bytecount"
@@ -543,9 +562,9 @@ checksum = "5ce89b21cab1437276d2650d57e971f9d548a2d9037cc231abdc0562b97498ce"
 
 [[package]]
 name = "bytemuck"
-version = "1.20.0"
+version = "1.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8b37c88a63ffd85d15b406896cc343916d7cf57838a847b3a6f2ca5d39a5695a"
+checksum = "ef657dfab802224e671f5818e9a4935f9b1957ed18e58292690cc39e7a4092a3"
 
 [[package]]
 name = "byteorder"
@@ -561,9 +580,9 @@ checksum = "8f1fe948ff07f4bd06c30984e69f5b4899c516a3ef74f34df92a2df2ab535495"
 
 [[package]]
 name = "bytes"
-version = "1.8.0"
+version = "1.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9ac0150caa2ae65ca5bd83f25c7de183dea78d4d366469f148435e2acfbad0da"
+checksum = "325918d6fe32f23b19878fe4b34794ae41fc19ddbe53b10571a4874d44ffd39b"
 
 [[package]]
 name = "camino"
@@ -576,9 +595,9 @@ dependencies = [
 
 [[package]]
 name = "cargo-platform"
-version = "0.1.8"
+version = "0.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "24b1f0365a6c6bb4020cd05806fd0d33c44d38046b8bd7f0e40814b9763cabfc"
+checksum = "e35af189006b9c0f00a064685c727031e3ed2d8020f7ba284d78cc2671bd36ea"
 dependencies = [
  "serde",
 ]
@@ -594,7 +613,7 @@ dependencies = [
  "semver",
  "serde",
  "serde_json",
- "thiserror",
+ "thiserror 1.0.69",
 ]
 
 [[package]]
@@ -620,9 +639,9 @@ dependencies = [
 
 [[package]]
 name = "cc"
-version = "1.2.1"
+version = "1.2.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fd9de9f2205d5ef3fd67e685b0df337994ddd4495e2a28d185500d0e1edfea47"
+checksum = "13208fcbb66eaeffe09b99fffbe1af420f00a7b35aa99ad683dfc1aa76145229"
 dependencies = [
  "jobserver",
  "libc",
@@ -704,9 +723,9 @@ dependencies = [
 
 [[package]]
 name = "clap"
-version = "4.5.21"
+version = "4.5.27"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fb3b4b9e5a7c7514dfa52869339ee98b3156b0bfb4e8a77c4ff4babb64b1604f"
+checksum = "769b0145982b4b48713e01ec42d61614425f27b7058bda7180a3a41f30104796"
 dependencies = [
  "clap_builder",
  "clap_derive",
@@ -714,9 +733,9 @@ dependencies = [
 
 [[package]]
 name = "clap_builder"
-version = "4.5.21"
+version = "4.5.27"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b17a95aa67cc7b5ebd32aa5370189aa0d79069ef1c64ce893bd30fb24bff20ec"
+checksum = "1b26884eb4b57140e4d2d93652abfa49498b938b3c9179f9fc487b0acc3edad7"
 dependencies = [
  "anstream",
  "anstyle",
@@ -726,27 +745,27 @@ dependencies = [
 
 [[package]]
 name = "clap_derive"
-version = "4.5.18"
+version = "4.5.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4ac6a0c7b1a9e9a5186361f67dfa1b88213572f427fb9ab038efb2bd8c582dab"
+checksum = "54b755194d6389280185988721fffba69495eed5ee9feeee9a599b53db80318c"
 dependencies = [
  "heck 0.5.0",
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
 name = "clap_lex"
-version = "0.7.3"
+version = "0.7.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "afb84c814227b90d6895e01398aee0d8033c00e7466aca416fb6a8e0eb19d8a7"
+checksum = "f46ad14479a25103f283c0f10005961cf086d8dc42205bb44c46ac563475dca6"
 
 [[package]]
 name = "cmake"
-version = "0.1.51"
+version = "0.1.53"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fb1e43aa7fd152b1f968787f7dbcdeb306d1867ff373c69955211876c053f91a"
+checksum = "e24a03c8b52922d68a1589ad61032f2c1aa5a8158d2aa0d93c6e9534944bbad6"
 dependencies = [
  "cc",
 ]
@@ -775,9 +794,9 @@ checksum = "5b63caa9aa9397e2d9480a9b13673856c78d8ac123288526c37d7839f2a86990"
 
 [[package]]
 name = "compact_str"
-version = "0.8.0"
+version = "0.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6050c3a16ddab2e412160b31f2c871015704239bca62f72f6e5f0be631d3f644"
+checksum = "3b79c4069c6cad78e2e0cdfcbd26275770669fb39fd308a752dc110e83b9af32"
 dependencies = [
  "castaway",
  "cfg-if",
@@ -789,15 +808,15 @@ dependencies = [
 
 [[package]]
 name = "console"
-version = "0.15.8"
+version = "0.15.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0e1f83fc076bd6dd27517eacdf25fef6c4dfe5f1d7448bafaaf3a26f13b5e4eb"
+checksum = "ea3c6ecd8059b57859df5c69830340ed3c41d30e3da0c1cbed90a96ac853041b"
 dependencies = [
  "encode_unicode",
- "lazy_static",
  "libc",
- "unicode-width 0.1.14",
- "windows-sys 0.52.0",
+ "once_cell",
+ "unicode-width 0.2.0",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
@@ -828,9 +847,9 @@ checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
 
 [[package]]
 name = "cpufeatures"
-version = "0.2.16"
+version = "0.2.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "16b80225097f2e5ae4e7179dd2266824648f3e2f49d9134d584b76389d31c4c3"
+checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280"
 dependencies = [
  "libc",
 ]
@@ -882,18 +901,18 @@ dependencies = [
 
 [[package]]
 name = "crossbeam-channel"
-version = "0.5.13"
+version = "0.5.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "33480d6946193aa8033910124896ca395333cae7e2d1113d1fef6c3272217df2"
+checksum = "06ba6d68e24814cb8de6bb986db8222d3a027d15872cabc0d18817bc3c0e4471"
 dependencies = [
  "crossbeam-utils",
 ]
 
 [[package]]
 name = "crossbeam-deque"
-version = "0.8.5"
+version = "0.8.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "613f8cc01fe9cf1a3eb3d7f488fd2fa8388403e97039e2f73692932e291a770d"
+checksum = "9dd111b7b7f7d55b72c0a6ae361660ee5853c9af73f70c3c2ef6858b950e2e51"
 dependencies = [
  "crossbeam-epoch",
  "crossbeam-utils",
@@ -910,9 +929,9 @@ dependencies = [
 
 [[package]]
 name = "crossbeam-utils"
-version = "0.8.20"
+version = "0.8.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "22ec99545bb0ed0ea7bb9b8e1e9122ea386ff8a48c0922e43f36d45ab09e0e80"
+checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
 
 [[package]]
 name = "crossterm"
@@ -920,7 +939,7 @@ version = "0.28.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "829d955a0bb380ef178a640b91779e3987da38c9aea133b20614cfed8cdea9c6"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.8.0",
  "crossterm_winapi",
  "mio",
  "parking_lot",
@@ -941,9 +960,9 @@ dependencies = [
 
 [[package]]
 name = "crunchy"
-version = "0.2.2"
+version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7a81dae078cea95a014a339291cec439d2f232ebe854a9d672b796c6afafa9b7"
+checksum = "43da5946c66ffcc7745f48db692ffbb10a83bfe0afd96235c5c2a4fb23994929"
 
 [[package]]
 name = "crypto-common"
@@ -988,46 +1007,61 @@ dependencies = [
 
 [[package]]
 name = "cxx"
-version = "1.0.130"
+version = "1.0.137"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "23c042a0ba58aaff55299632834d1ea53ceff73d62373f62c9ae60890ad1b942"
+checksum = "0fc894913dccfed0f84106062c284fa021c3ba70cb1d78797d6f5165d4492e45"
 dependencies = [
  "cc",
+ "cxxbridge-cmd",
  "cxxbridge-flags",
  "cxxbridge-macro",
+ "foldhash",
  "link-cplusplus",
 ]
 
 [[package]]
 name = "cxx-build"
-version = "1.0.130"
+version = "1.0.137"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "45dc1c88d0fdac57518a9b1f6c4f4fb2aca8f3c30c0d03d7d8518b47ca0bcea6"
+checksum = "503b2bfb6b3e8ce7f95d865a67419451832083d3186958290cee6c53e39dfcfe"
 dependencies = [
  "cc",
  "codespan-reporting",
  "proc-macro2",
  "quote",
  "scratch",
- "syn 2.0.89",
+ "syn 2.0.96",
+]
+
+[[package]]
+name = "cxxbridge-cmd"
+version = "1.0.137"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e0d2cb64a95b4b5a381971482235c4db2e0208302a962acdbe314db03cbbe2fb"
+dependencies = [
+ "clap 4.5.27",
+ "codespan-reporting",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.96",
 ]
 
 [[package]]
 name = "cxxbridge-flags"
-version = "1.0.130"
+version = "1.0.137"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aa7ed7d30b289e2592cc55bc2ccd89803a63c913e008e6eb59f06cddf45bb52f"
+checksum = "5f797b0206463c9c2a68ed605ab28892cca784f1ef066050f4942e3de26ad885"
 
 [[package]]
 name = "cxxbridge-macro"
-version = "1.0.130"
+version = "1.0.137"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b8c465d22de46b851c04630a5fc749a26005b263632ed2e0d9cc81518ead78d"
+checksum = "e79010a2093848e65a3e0f7062d3f02fb2ef27f866416dfe436fccfa73d3bb59"
 dependencies = [
  "proc-macro2",
  "quote",
  "rustversion",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -1051,7 +1085,7 @@ dependencies = [
  "proc-macro2",
  "quote",
  "strsim",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -1062,7 +1096,7 @@ checksum = "d336a2a514f6ccccaa3e09b02d41d35330c07ddf03a62165fcec10bb561c7806"
 dependencies = [
  "darling_core",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -1092,7 +1126,7 @@ dependencies = [
  "darling",
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -1102,15 +1136,9 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ab63b0e2bf4d5928aff72e83a7dace85d7bba5fe12dcc3c5a572d78caffd3f3c"
 dependencies = [
  "derive_builder_core",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
-[[package]]
-name = "diff"
-version = "0.1.13"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "56254986775e3233ffa9c4d7d3faaf6d36a2c09d30b20687e9f88bc8bafc16c8"
-
 [[package]]
 name = "digest"
 version = "0.10.7"
@@ -1150,7 +1178,7 @@ checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -1161,9 +1189,9 @@ checksum = "92773504d58c093f6de2459af4af33faa518c13451eb8f2b5698ed3d36e7c813"
 
 [[package]]
 name = "easy-cast"
-version = "0.5.2"
+version = "0.5.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "10936778145f3bea71fd9bf61332cce28c28e96a380714f7ab34838b80733fd6"
+checksum = "72852736692ec862655eca398c9bb1b476161b563c9f80f45f4808b9629750d6"
 dependencies = [
  "libm",
 ]
@@ -1185,9 +1213,9 @@ dependencies = [
 
 [[package]]
 name = "encode_unicode"
-version = "0.3.6"
+version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a357d28ed41a50f9c765dbfe56cbc04a64e53e5fc58ba79fbc34c10ef3df831f"
+checksum = "34aa73646ffb006b8f5147f3dc182bd4bcb190227ce861fc4a4844bf8e3cb2c0"
 
 [[package]]
 name = "encoding_rs"
@@ -1206,12 +1234,12 @@ checksum = "5443807d6dff69373d433ab9ef5378ad8df50ca6298caf15de6e52e24aaf54d5"
 
 [[package]]
 name = "errno"
-version = "0.3.9"
+version = "0.3.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "534c5cf6194dfab3db3242765c03bbe257cf92f22b38f6bc0c58d59108a820ba"
+checksum = "33d852cb9b869c2a9b3df2f71a3074817f01e1844f839a144f5fcef059a4eb5d"
 dependencies = [
  "libc",
- "windows-sys 0.52.0",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
@@ -1251,15 +1279,15 @@ dependencies = [
 
 [[package]]
 name = "fastrand"
-version = "2.2.0"
+version = "2.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "486f806e73c5707928240ddc295403b1b93c96a02038563881c4a2fd84b81ac4"
+checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
 
 [[package]]
 name = "fdeflate"
-version = "0.3.6"
+version = "0.3.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "07c6f4c64c1d33a3111c4466f7365ebdcc37c5bd1ea0d62aae2e3d722aacbedb"
+checksum = "1e6853b52649d4ac5c0bd02320cddc5ba956bdb407c4b75a2c6b75bf51500f8c"
 dependencies = [
  "simd-adler32",
 ]
@@ -1311,9 +1339,9 @@ checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
 
 [[package]]
 name = "foldhash"
-version = "0.1.3"
+version = "0.1.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f81ec6369c545a7d40e4589b5597581fa1c441fe1cce96dd1de43159910a36a2"
+checksum = "a0d2fde1f7b3d48b8395d5f2de76c18a528bd6a9cdde438df747bfcba3e05d6f"
 
 [[package]]
 name = "foreign-types"
@@ -1411,7 +1439,7 @@ checksum = "162ee34ebcb7c64a8abebc059ce0fee27c2262618d7b60ed8faf72fef13c3650"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -1471,7 +1499,19 @@ checksum = "c4567c8db10ae91089c99af84c68c38da3ec2f087c3f82960bcdbf3656b6f4d7"
 dependencies = [
  "cfg-if",
  "libc",
- "wasi",
+ "wasi 0.11.0+wasi-snapshot-preview1",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "43a49c392881ce6d5c3b8cb70f98717b7c07aabbdff06687b9030dbfbe2725f8"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "wasi 0.13.3+wasi-0.2.2",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -1492,9 +1532,9 @@ checksum = "07e28edb80900c19c28f1072f2e8aeca7fa06b23cd4169cefe1af5aa3260783f"
 
 [[package]]
 name = "glob"
-version = "0.3.1"
+version = "0.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
+checksum = "a8d1add55171497b4705a648c6b583acafb01d58050a51727785f0b2c8e0a2b2"
 
 [[package]]
 name = "grpc-metadata"
@@ -1518,7 +1558,7 @@ dependencies = [
  "futures-sink",
  "futures-util",
  "http 0.2.12",
- "indexmap 2.6.0",
+ "indexmap 2.7.1",
  "slab",
  "tokio",
  "tokio-util",
@@ -1536,8 +1576,8 @@ dependencies = [
  "fnv",
  "futures-core",
  "futures-sink",
- "http 1.1.0",
- "indexmap 2.6.0",
+ "http 1.2.0",
+ "indexmap 2.7.1",
  "slab",
  "tokio",
  "tokio-util",
@@ -1577,9 +1617,9 @@ dependencies = [
 
 [[package]]
 name = "hashbrown"
-version = "0.15.1"
+version = "0.15.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3a9bfc1af68b1726ea47d3d5109de126281def866b33970e10fbab11b5dafab3"
+checksum = "bf151400ff0baff5465007dd2f3e717f3fe502074ca563069ce3a6629d07b289"
 dependencies = [
  "allocator-api2",
  "equivalent",
@@ -1629,18 +1669,18 @@ dependencies = [
  "reqwest 0.11.27",
  "serde",
  "serde_json",
- "thiserror",
+ "thiserror 1.0.69",
  "tokio",
  "ureq",
 ]
 
 [[package]]
 name = "home"
-version = "0.5.9"
+version = "0.5.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e3d1354bf6b7235cb4a0576c2619fd4ed18183f689b12b006a0ee7329eeff9a5"
+checksum = "589533453244b0995c858700322199b2becb13b627df2851f64a2775d024abcf"
 dependencies = [
- "windows-sys 0.52.0",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
@@ -1667,9 +1707,9 @@ dependencies = [
 
 [[package]]
 name = "http"
-version = "1.1.0"
+version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "21b9ddb458710bc376481b842f5da65cdf31522de232c1ca8146abce2a358258"
+checksum = "f16ca2af56261c99fba8bac40a10251ce8188205a4c448fbb745a2e4daa76fea"
 dependencies = [
  "bytes",
  "fnv",
@@ -1694,7 +1734,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1efedce1fb8e6913f23e0c92de8e62cd5b772a67e7b3946df930a62566c93184"
 dependencies = [
  "bytes",
- "http 1.1.0",
+ "http 1.2.0",
 ]
 
 [[package]]
@@ -1705,16 +1745,16 @@ checksum = "793429d76616a256bcb62c2a2ec2bed781c8307e797e2598c50010f2bee2544f"
 dependencies = [
  "bytes",
  "futures-util",
- "http 1.1.0",
+ "http 1.2.0",
  "http-body 1.0.1",
  "pin-project-lite",
 ]
 
 [[package]]
 name = "httparse"
-version = "1.9.5"
+version = "1.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7d71d3574edd2771538b901e6549113b4006ece66150fb69c0fb6d9a2adae946"
+checksum = "f2d708df4e7140240a16cd6ab0ab65c972d7433ab77819ea693fde9c43811e2a"
 
 [[package]]
 name = "httpdate"
@@ -1724,9 +1764,9 @@ checksum = "df3b46402a9d5adb4c86a0cf463f42e19994e3ee891101b1841f30a545cb49a9"
 
 [[package]]
 name = "hyper"
-version = "0.14.31"
+version = "0.14.32"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8c08302e8fa335b151b788c775ff56e7a03ae64ff85c548ee820fecb70356e85"
+checksum = "41dfc780fdec9373c01bae43289ea34c972e40ee3c9f6b3c8801a35f35586ce7"
 dependencies = [
  "bytes",
  "futures-channel",
@@ -1748,15 +1788,15 @@ dependencies = [
 
 [[package]]
 name = "hyper"
-version = "1.5.1"
+version = "1.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "97818827ef4f364230e16705d4706e2897df2bb60617d6ca15d598025a3c481f"
+checksum = "cc2b571658e38e0c01b1fdca3bbbe93c00d3d71693ff2770043f8c29bc7d6f80"
 dependencies = [
  "bytes",
  "futures-channel",
  "futures-util",
  "h2 0.4.7",
- "http 1.1.0",
+ "http 1.2.0",
  "http-body 1.0.1",
  "httparse",
  "httpdate",
@@ -1769,16 +1809,16 @@ dependencies = [
 
 [[package]]
 name = "hyper-rustls"
-version = "0.27.3"
+version = "0.27.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "08afdbb5c31130e3034af566421053ab03787c640246a446327f550d11bcb333"
+checksum = "2d191583f3da1305256f22463b9bb0471acad48a4e534a5218b9963e9c1f59b2"
 dependencies = [
  "futures-util",
- "http 1.1.0",
- "hyper 1.5.1",
+ "http 1.2.0",
+ "hyper 1.6.0",
  "hyper-util",
  "log",
- "rustls 0.23.17",
+ "rustls 0.23.21",
  "rustls-native-certs",
  "rustls-pki-types",
  "tokio",
@@ -1792,7 +1832,7 @@ version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bbb958482e8c7be4bc3cf272a766a2b0bf1a6755e7a6ae777f017a31d11b13b1"
 dependencies = [
- "hyper 0.14.31",
+ "hyper 0.14.32",
  "pin-project-lite",
  "tokio",
  "tokio-io-timeout",
@@ -1805,7 +1845,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d6183ddfa99b85da61a140bea0efc93fdf56ceaa041b37d553518030827f9905"
 dependencies = [
  "bytes",
- "hyper 0.14.31",
+ "hyper 0.14.32",
  "native-tls",
  "tokio",
  "tokio-native-tls",
@@ -1820,9 +1860,9 @@ dependencies = [
  "bytes",
  "futures-channel",
  "futures-util",
- "http 1.1.0",
+ "http 1.2.0",
  "http-body 1.0.1",
- "hyper 1.5.1",
+ "hyper 1.6.0",
  "pin-project-lite",
  "socket2",
  "tokio",
@@ -1968,7 +2008,7 @@ checksum = "1ec89e9337638ecdc08744df490b221a7399bf8d164eb52a665454e60e075ad6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -2023,9 +2063,9 @@ dependencies = [
 
 [[package]]
 name = "image-webp"
-version = "0.2.0"
+version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e031e8e3d94711a9ccb5d6ea357439ef3dcbed361798bd4071dc4d9793fbe22f"
+checksum = "b77d01e822461baa8409e156015a1d91735549f0f2c17691bd2d996bef238f7f"
 dependencies = [
  "byteorder-lite",
  "quick-error",
@@ -2049,20 +2089,20 @@ dependencies = [
 
 [[package]]
 name = "indexmap"
-version = "2.6.0"
+version = "2.7.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "707907fe3c25f5424cce2cb7e1cbcafee6bdbe735ca90ef77c29e84591e5b9da"
+checksum = "8c9c992b02b5b4c94ea26e32fe5bccb7aa7d9f390ab5c1221ff895bc7ea8b652"
 dependencies = [
  "equivalent",
- "hashbrown 0.15.1",
+ "hashbrown 0.15.2",
  "serde",
 ]
 
 [[package]]
 name = "indicatif"
-version = "0.17.9"
+version = "0.17.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cbf675b85ed934d3c67b5c5469701eec7db22689d0a2139d856e0925fa28b281"
+checksum = "183b3088984b400f4cfac3620d5e076c84da5364016b4f49473de574b2586235"
 dependencies = [
  "console",
  "number_prefix",
@@ -2085,23 +2125,22 @@ checksum = "94bd26b1b737bc11f183620072e188d1c6ede67e0e78682228d66b49ec510e17"
 dependencies = [
  "opentelemetry 0.20.0",
  "opentelemetry-otlp",
- "thiserror",
+ "thiserror 1.0.69",
  "tracing",
  "tracing-opentelemetry 0.21.0",
 ]
 
 [[package]]
 name = "instability"
-version = "0.3.3"
+version = "0.3.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b829f37dead9dc39df40c2d3376c179fdfd2ac771f53f55d3c30dc096a3c0c6e"
+checksum = "0bf9fed6d91cfb734e7476a06bde8300a1b94e217e1b523b6f0cd1a01998c71d"
 dependencies = [
  "darling",
  "indoc",
- "pretty_assertions",
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -2112,14 +2151,14 @@ checksum = "c34819042dc3d3971c46c2190835914dfbe0c3c13f61449b2997f4e9722dfa60"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
 name = "ipnet"
-version = "2.10.1"
+version = "2.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ddc24109865250148c2e0f3d25d4f0f479571723792d3802153c60922a4fb708"
+checksum = "469fb0b9cefa57e3ef31275ee7cacb78f2fdca44e4765491884a2b119d4eb130"
 
 [[package]]
 name = "is_terminal_polyfill"
@@ -2165,9 +2204,9 @@ dependencies = [
 
 [[package]]
 name = "itoa"
-version = "1.0.13"
+version = "1.0.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "540654e97a3f4470a492cd30ff187bc95d89557a903a2bbf112e2fae98104ef2"
+checksum = "d75a2a4b1b190afb6f5425f10f6a8f959d2ea0b9c2b1d79553551850539e4674"
 
 [[package]]
 name = "jobserver"
@@ -2186,18 +2225,19 @@ checksum = "f5d4a7da358eff58addd2877a45865158f0d78c911d43a5784ceb7bbf52833b0"
 
 [[package]]
 name = "js-sys"
-version = "0.3.72"
+version = "0.3.77"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6a88f1bda2bd75b0452a14784937d796722fdebfe50df998aeb3f0b7603019a9"
+checksum = "1cfaf33c695fc6e08064efbc1f72ec937429614f25eef83af942d0e227c3a28f"
 dependencies = [
+ "once_cell",
  "wasm-bindgen",
 ]
 
 [[package]]
 name = "jsonschema"
-version = "0.28.0"
+version = "0.28.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "74d8eb539cdb4222da29bb658cc9881aa2477b33fb1a74c5c31450395fc1a4b2"
+checksum = "4b8f66fe41fa46a5c83ed1c717b7e0b4635988f427083108c8cf0a882cc13441"
 dependencies = [
  "ahash",
  "base64 0.22.1",
@@ -2212,7 +2252,7 @@ dependencies = [
  "percent-encoding",
  "referencing",
  "regex-syntax 0.8.5",
- "reqwest 0.12.9",
+ "reqwest 0.12.12",
  "serde",
  "serde_json",
  "uuid-simd",
@@ -2244,9 +2284,9 @@ checksum = "b5aba8db14291edd000dfcc4d620c7ebfb122c613afb886ca8803fa4e128a20a"
 
 [[package]]
 name = "libfuzzer-sys"
-version = "0.4.8"
+version = "0.4.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9b9569d2f74e257076d8c6bfa73fb505b46b851e51ddaecc825944aa3bed17fa"
+checksum = "cf78f52d400cf2d84a3a973a78a592b4adc535739e0a5597a0da6f0c357adc75"
 dependencies = [
  "arbitrary",
  "cc",
@@ -2254,9 +2294,9 @@ dependencies = [
 
 [[package]]
 name = "libloading"
-version = "0.8.5"
+version = "0.8.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4979f22fdb869068da03c9f7528f8297c6fd2606bc3a4affe42e6a823fdb8da4"
+checksum = "fc2f4eb4bc735547cfed7c0a4922cbd04a4655978c09b54f1f7b228750664c34"
 dependencies = [
  "cfg-if",
  "windows-targets 0.52.6",
@@ -2274,7 +2314,7 @@ version = "0.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c0ff37bd590ca25063e35af745c343cb7a0271906fb7b37e4813e8f79f00268d"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.8.0",
  "libc",
 ]
 
@@ -2289,15 +2329,15 @@ dependencies = [
 
 [[package]]
 name = "linux-raw-sys"
-version = "0.4.14"
+version = "0.4.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "78b3ae25bc7c8c38cec158d1f2757ee79e9b3740fbc7ccf0e59e4b08d793fa89"
+checksum = "d26c52dbd32dccf2d10cac7725f8eae5296885fb5703b261f7d0a0739ec807ab"
 
 [[package]]
 name = "litemap"
-version = "0.7.3"
+version = "0.7.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "643cb0b8d4fcc284004d5fd0d67ccf61dfffadb7f75e1e71bc420f4688a3a704"
+checksum = "4ee93343901ab17bd981295f2cf0026d4ad018c7c31ba84549a4ddbb47a45104"
 
 [[package]]
 name = "lock_api"
@@ -2311,9 +2351,9 @@ dependencies = [
 
 [[package]]
 name = "log"
-version = "0.4.22"
+version = "0.4.25"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a7a70ba024b9dc04c27ea2f0c0548feb474ec5c54bba33a7f72f873a39d07b24"
+checksum = "04cbf5b083de1c7e0222a7a51dbfdba1cbe1c6ab0b15e29fff3f6c077fd9cd9f"
 
 [[package]]
 name = "loop9"
@@ -2330,7 +2370,7 @@ version = "0.12.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "234cf4f4a04dc1f57e24b96cc0cd600cf2af460d4161ac5ecdd0af8e1f3b2a38"
 dependencies = [
- "hashbrown 0.15.1",
+ "hashbrown 0.15.2",
 ]
 
 [[package]]
@@ -2413,15 +2453,15 @@ checksum = "b4f0c8427b39666bf970460908b213ec09b3b350f20c0c2eabcbba51704a08e6"
 dependencies = [
  "base64 0.22.1",
  "http-body-util",
- "hyper 1.5.1",
+ "hyper 1.6.0",
  "hyper-rustls",
  "hyper-util",
- "indexmap 2.6.0",
+ "indexmap 2.7.1",
  "ipnet",
  "metrics",
  "metrics-util",
  "quanta",
- "thiserror",
+ "thiserror 1.0.69",
  "tokio",
  "tracing",
 ]
@@ -2459,9 +2499,9 @@ dependencies = [
 
 [[package]]
 name = "minijinja"
-version = "2.5.0"
+version = "2.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2c37e1b517d1dcd0e51dc36c4567b9d5a29262b3ec8da6cb5d35e27a8fb529b5"
+checksum = "cff7b8df5e85e30b87c2b0b3f58ba3a87b68e133738bf512a7713769326dbca9"
 dependencies = [
  "serde",
  "serde_json",
@@ -2469,9 +2509,9 @@ dependencies = [
 
 [[package]]
 name = "minijinja-contrib"
-version = "2.5.0"
+version = "2.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7fe51f1a6a8285f03fcd1544d834234fe8db285f29e1c2253600c93b3ae19242"
+checksum = "7ac3e47a9006ed0500425a092c9f8b2e56d10f8aeec8ce870c5e8a7c6ef2d7c3"
 dependencies = [
  "minijinja",
  "serde",
@@ -2485,9 +2525,9 @@ checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
 
 [[package]]
 name = "miniz_oxide"
-version = "0.8.0"
+version = "0.8.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e2d80299ef12ff69b16a84bb182e3b9df68b5a91574d3d4fa6e41b65deec4df1"
+checksum = "b8402cab7aefae129c6977bb0ff1b8fd9a04eb5b51efc50a70bea51cda0c7924"
 dependencies = [
  "adler2",
  "simd-adler32",
@@ -2495,23 +2535,16 @@ dependencies = [
 
 [[package]]
 name = "mio"
-version = "1.0.2"
+version = "1.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "80e04d1dcff3aae0704555fe5fee3bcfaf3d1fdf8a7e521d5b9d2b42acb52cec"
+checksum = "2886843bf800fba2e3377cff24abf6379b4c4d5c6681eaf9ea5b0d15090450bd"
 dependencies = [
- "hermit-abi 0.3.9",
  "libc",
  "log",
- "wasi",
+ "wasi 0.11.0+wasi-snapshot-preview1",
  "windows-sys 0.52.0",
 ]
 
-[[package]]
-name = "mirai-annotations"
-version = "1.12.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c9be0862c1b3f26a88803c4a49de6889c10e608b3ee9344e6ef5b45fb37ad3d1"
-
 [[package]]
 name = "monostate"
 version = "0.1.13"
@@ -2530,7 +2563,7 @@ checksum = "a7ce64b975ed4f123575d11afd9491f2e37bbd5813fbfbc0f09ae1fbddea74e0"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -2552,7 +2585,7 @@ dependencies = [
  "futures",
  "pin-project",
  "rand",
- "thiserror",
+ "thiserror 1.0.69",
  "tokio",
  "tokio-util",
  "tracing",
@@ -2560,9 +2593,9 @@ dependencies = [
 
 [[package]]
 name = "native-tls"
-version = "0.2.12"
+version = "0.2.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a8614eb2c83d59d1c8cc974dd3f920198647674a0a035e1af1fa58707e317466"
+checksum = "0dab59f8e050d5df8e4dd87d9206fb6f65a483e20ac9fda365ade4fab353196c"
 dependencies = [
  "libc",
  "log",
@@ -2596,7 +2629,7 @@ dependencies = [
  "bytes",
  "futures",
  "hostname",
- "hyper 0.14.31",
+ "hyper 0.14.32",
  "muxado",
  "once_cell",
  "parking_lot",
@@ -2604,7 +2637,7 @@ dependencies = [
  "rustls-pemfile",
  "serde",
  "serde_json",
- "thiserror",
+ "thiserror 1.0.69",
  "tokio",
  "tokio-retry",
  "tokio-util",
@@ -2618,7 +2651,7 @@ version = "0.28.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ab2156c4fce2f8df6c499cc1c763e4394b7482525bf2a9701c9d79d215f519e4"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.8.0",
  "cfg-if",
  "cfg_aliases 0.1.1",
  "libc",
@@ -2630,7 +2663,7 @@ version = "0.29.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "71e2746dc3a24dd78b3cfcb7be93368c6de9963d30f43a6a73998a9cf4b17b46"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.8.0",
  "cfg-if",
  "cfg_aliases 0.2.1",
  "libc",
@@ -2730,7 +2763,7 @@ checksum = "ed3955f1a9c7c0c15e092f9c887db08b1fc683305fdf6eb6684f22555355e202"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -2801,9 +2834,9 @@ checksum = "830b246a0e5f20af87141b25c173cd1b609bd7779a4617d6ec582abaf90870f3"
 
 [[package]]
 name = "object"
-version = "0.36.5"
+version = "0.36.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aedf0a2d09c573ed1d8d85b30c119153926a2b36dce0ab28322c09a117a4683e"
+checksum = "62948e14d923ea95ea2c7c86c71013138b66525b86bdc08d2dcc262bdb497b87"
 dependencies = [
  "memchr",
 ]
@@ -2844,11 +2877,11 @@ checksum = "b410bbe7e14ab526a0e86877eb47c6996a2bd7746f027ba551028c925390e4e9"
 
 [[package]]
 name = "openssl"
-version = "0.10.68"
+version = "0.10.69"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6174bc48f102d208783c2c84bf931bb75927a617866870de8a4ea85597f871f5"
+checksum = "f5e534d133a060a3c19daec1eb3e98ec6f4685978834f2dbadfe2ec215bab64e"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.8.0",
  "cfg-if",
  "foreign-types",
  "libc",
@@ -2865,14 +2898,14 @@ checksum = "a948666b637a0f465e8564c73e89d4dde00d72d4d473cc972f390fc3dcee7d9c"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
 name = "openssl-probe"
-version = "0.1.5"
+version = "0.1.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ff011a302c396a5197692431fc1948019154afc178baf7d8e37367442a4601cf"
+checksum = "d05e27ee213611ffe7d6348b942e8f942b37114c00cc03cec254295a4a17852e"
 
 [[package]]
 name = "openssl-sys"
@@ -2904,11 +2937,11 @@ checksum = "1e32339a5dc40459130b3bd269e9892439f55b33e772d2a9d402a789baaf4e8a"
 dependencies = [
  "futures-core",
  "futures-sink",
- "indexmap 2.6.0",
+ "indexmap 2.7.1",
  "js-sys",
  "once_cell",
  "pin-project-lite",
- "thiserror",
+ "thiserror 1.0.69",
  "urlencoding",
 ]
 
@@ -2926,7 +2959,7 @@ dependencies = [
  "opentelemetry_api",
  "opentelemetry_sdk 0.20.0",
  "prost 0.11.9",
- "thiserror",
+ "thiserror 1.0.69",
  "tokio",
  "tonic 0.9.2",
 ]
@@ -2964,7 +2997,7 @@ dependencies = [
  "js-sys",
  "once_cell",
  "pin-project-lite",
- "thiserror",
+ "thiserror 1.0.69",
  "urlencoding",
 ]
 
@@ -2986,7 +3019,7 @@ dependencies = [
  "rand",
  "regex",
  "serde_json",
- "thiserror",
+ "thiserror 1.0.69",
  "tokio",
  "tokio-stream",
 ]
@@ -3005,10 +3038,10 @@ dependencies = [
  "glob",
  "once_cell",
  "opentelemetry 0.21.0",
- "ordered-float 4.5.0",
+ "ordered-float 4.6.0",
  "percent-encoding",
  "rand",
- "thiserror",
+ "thiserror 1.0.69",
 ]
 
 [[package]]
@@ -3028,9 +3061,9 @@ dependencies = [
 
 [[package]]
 name = "ordered-float"
-version = "4.5.0"
+version = "4.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c65ee1f9701bf938026630b455d5315f490640234259037edb259798b3bcf85e"
+checksum = "7bb71e1b3fa6ca1c61f383464aaf2bb0e2f8e772a1f01d486832464de363b951"
 dependencies = [
  "num-traits",
 ]
@@ -3048,9 +3081,9 @@ dependencies = [
 
 [[package]]
 name = "outref"
-version = "0.5.1"
+version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4030760ffd992bef45b0ae3f10ce1aba99e33464c90d14dd7c039884963ddc7a"
+checksum = "1a80800c0488c3a21695ea981a54918fbb37abf04f4d0720c453632255e2ff0e"
 
 [[package]]
 name = "overload"
@@ -3111,34 +3144,34 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b4c5cc86750666a3ed20bdaf5ca2a0344f9c67674cae0515bec2da16fbaa47db"
 dependencies = [
  "fixedbitset",
- "indexmap 2.6.0",
+ "indexmap 2.7.1",
 ]
 
 [[package]]
 name = "pin-project"
-version = "1.1.7"
+version = "1.1.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "be57f64e946e500c8ee36ef6331845d40a93055567ec57e8fae13efd33759b95"
+checksum = "1e2ec53ad785f4d35dac0adea7f7dc6f1bb277ad84a680c7afefeae05d1f5916"
 dependencies = [
  "pin-project-internal",
 ]
 
 [[package]]
 name = "pin-project-internal"
-version = "1.1.7"
+version = "1.1.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3c0f5fad0874fc7abcd4d750e76917eaebbecaa2c20bde22e1dbeeba8beb758c"
+checksum = "d56a66c0c55993aa927429d0f8a0abfd74f084e4d9c192cffed01e418d83eefb"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
 name = "pin-project-lite"
-version = "0.2.15"
+version = "0.2.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "915a1e146535de9163f3987b8944ed8cf49a18bb0056bcebcdcece385cece4ff"
+checksum = "3b3cff922bd51709b605d9ead9aa71031d81447142d828eb4a6eba76fe619f9b"
 
 [[package]]
 name = "pin-utils"
@@ -3182,9 +3215,9 @@ dependencies = [
 
 [[package]]
 name = "png"
-version = "0.17.14"
+version = "0.17.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "52f9d46a34a05a6a57566bc2bfae066ef07585a6e3fa30fbbdff5936380623f0"
+checksum = "82151a2fc869e011c153adc57cf2789ccb8d9906ce52c0b39a6b5697749d7526"
 dependencies = [
  "bitflags 1.3.2",
  "crc32fast",
@@ -3195,9 +3228,9 @@ dependencies = [
 
 [[package]]
 name = "portable-atomic"
-version = "1.9.0"
+version = "1.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cc9c68a3f6da06753e9335d63e27f6b9754dd1920d941135b7ea8224f141adb2"
+checksum = "280dc24453071f1b63954171985a0b0d30058d287960968b9b2aca264c8d4ee6"
 
 [[package]]
 name = "powerfmt"
@@ -3214,24 +3247,14 @@ dependencies = [
  "zerocopy",
 ]
 
-[[package]]
-name = "pretty_assertions"
-version = "1.4.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3ae130e2f271fbc2ac3a40fb1d07180839cdbbe443c7a27e1e3c13c5cac0116d"
-dependencies = [
- "diff",
- "yansi",
-]
-
 [[package]]
 name = "prettyplease"
-version = "0.2.25"
+version = "0.2.29"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "64d1ec885c64d0457d564db4ec299b2dae3f9c02808b8ad9c3a089c591b18033"
+checksum = "6924ced06e1f7dfe3fa48d57b9f74f55d8915f5036121bef647ef4b204895fac"
 dependencies = [
  "proc-macro2",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -3260,9 +3283,9 @@ dependencies = [
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.92"
+version = "1.0.93"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "37d3544b3f2748c54e147655edb5025752e2303145b5aefb3c3ea2c78b973bb0"
+checksum = "60946a68e5f9d28b0dc1c21bb8a97ee7d018a8b322fa57838ba31cc878e22d99"
 dependencies = [
  "unicode-ident",
 ]
@@ -3283,7 +3306,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a65f2e60fbf1063868558d69c6beacf412dc755f9fc020f514b7955fc914fe30"
 dependencies = [
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -3323,7 +3346,7 @@ dependencies = [
  "prost 0.12.6",
  "prost-types",
  "regex",
- "syn 2.0.89",
+ "syn 2.0.96",
  "tempfile",
 ]
 
@@ -3350,7 +3373,7 @@ dependencies = [
  "itertools 0.12.1",
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -3409,7 +3432,7 @@ dependencies = [
  "proc-macro2",
  "pyo3-macros-backend",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -3422,7 +3445,7 @@ dependencies = [
  "proc-macro2",
  "pyo3-build-config",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -3436,15 +3459,15 @@ dependencies = [
 
 [[package]]
 name = "quanta"
-version = "0.12.3"
+version = "0.12.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8e5167a477619228a0b284fac2674e3c388cba90631d7b7de620e6f1fcd08da5"
+checksum = "3bd1fe6824cea6538803de3ff1bc0cf3949024db3d43c9643024bfb33a807c0e"
 dependencies = [
  "crossbeam-utils",
  "libc",
  "once_cell",
  "raw-cpuid",
- "wasi",
+ "wasi 0.11.0+wasi-snapshot-preview1",
  "web-sys",
  "winapi",
 ]
@@ -3457,9 +3480,9 @@ checksum = "a993555f31e5a609f617c12db6250dedcac1b0a85076912c436e6fc9b2c8e6a3"
 
 [[package]]
 name = "quote"
-version = "1.0.37"
+version = "1.0.38"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b5b9d34b8991d19d98081b46eacdd8eb58c6f2b201139f7c5f643cc155a633af"
+checksum = "0e4dccaaaf89514f546c693ddc140f729f958c247918a13380cccc6078391acc"
 dependencies = [
  "proc-macro2",
 ]
@@ -3491,7 +3514,7 @@ version = "0.6.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
 dependencies = [
- "getrandom",
+ "getrandom 0.2.15",
 ]
 
 [[package]]
@@ -3500,7 +3523,7 @@ version = "0.28.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fdef7f9be5c0122f890d58bdf4d964349ba6a6161f705907526d891efabba57d"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.8.0",
  "cassowary",
  "compact_str",
  "crossterm",
@@ -3545,7 +3568,7 @@ dependencies = [
  "rand_chacha",
  "simd_helpers",
  "system-deps",
- "thiserror",
+ "thiserror 1.0.69",
  "v_frame",
  "wasm-bindgen",
 ]
@@ -3567,11 +3590,11 @@ dependencies = [
 
 [[package]]
 name = "raw-cpuid"
-version = "11.2.0"
+version = "11.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ab240315c661615f2ee9f0f2cd32d5a7343a84d5ebcccb99d46e6637565e7b0"
+checksum = "c6928fa44c097620b706542d428957635951bade7143269085389d42c8a4927e"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.8.0",
 ]
 
 [[package]]
@@ -3607,11 +3630,11 @@ dependencies = [
 
 [[package]]
 name = "redox_syscall"
-version = "0.5.7"
+version = "0.5.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9b6dfecf2c74bce2466cabf93f6664d6998a69eb21e39f4207930065b27b771f"
+checksum = "03a862b389f93e68874fbf580b9de08dd02facb9a788ebadaf4a3fd33cf58834"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.8.0",
 ]
 
 [[package]]
@@ -3620,9 +3643,9 @@ version = "0.4.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ba009ff324d1fc1b900bd1fdb31564febe58a8ccc8a6fdbb93b543d33b13ca43"
 dependencies = [
- "getrandom",
+ "getrandom 0.2.15",
  "libredox",
- "thiserror",
+ "thiserror 1.0.69",
 ]
 
 [[package]]
@@ -3642,14 +3665,14 @@ checksum = "bcc303e793d3734489387d205e9b186fac9c6cfacedd98cbb2e8a5943595f3e6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
 name = "referencing"
-version = "0.28.0"
+version = "0.28.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "093a875008827c0ae15c746189966e162faa05bf347719d06302c548ac63630f"
+checksum = "d0dcb5ab28989ad7c91eb1b9531a37a1a137cc69a0499aee4117cae4a107c464"
 dependencies = [
  "ahash",
  "fluent-uri",
@@ -3716,7 +3739,7 @@ dependencies = [
  "h2 0.3.26",
  "http 0.2.12",
  "http-body 0.4.6",
- "hyper 0.14.31",
+ "hyper 0.14.32",
  "hyper-tls",
  "ipnet",
  "js-sys",
@@ -3744,19 +3767,19 @@ dependencies = [
 
 [[package]]
 name = "reqwest"
-version = "0.12.9"
+version = "0.12.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a77c62af46e79de0a562e1a9849205ffcb7fc1238876e9bd743357570e04046f"
+checksum = "43e734407157c3c2034e0258f5e4473ddb361b1e85f95a66690d67264d7cd1da"
 dependencies = [
  "base64 0.22.1",
  "bytes",
  "futures-channel",
  "futures-core",
  "futures-util",
- "http 1.1.0",
+ "http 1.2.0",
  "http-body 1.0.1",
  "http-body-util",
- "hyper 1.5.1",
+ "hyper 1.6.0",
  "hyper-util",
  "ipnet",
  "js-sys",
@@ -3770,6 +3793,7 @@ dependencies = [
  "serde_urlencoded",
  "sync_wrapper 1.0.2",
  "tokio",
+ "tower 0.5.2",
  "tower-service",
  "url",
  "wasm-bindgen",
@@ -3807,7 +3831,7 @@ checksum = "c17fa4cb658e3583423e915b9f3acc01cceaee1860e33d59ebae66adc3a2dc0d"
 dependencies = [
  "cc",
  "cfg-if",
- "getrandom",
+ "getrandom 0.2.15",
  "libc",
  "spin 0.9.8",
  "untrusted 0.9.0",
@@ -3834,7 +3858,7 @@ dependencies = [
  "proc-macro2",
  "quote",
  "rust-embed-utils",
- "syn 2.0.89",
+ "syn 2.0.96",
  "walkdir",
 ]
 
@@ -3860,6 +3884,12 @@ version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
 
+[[package]]
+name = "rustc-hash"
+version = "2.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c7fb8039b3032c191086b10f11f319a6e99e1e82889c5cc6046f515c9db1d497"
+
 [[package]]
 name = "rustc_version"
 version = "0.4.1"
@@ -3871,15 +3901,15 @@ dependencies = [
 
 [[package]]
 name = "rustix"
-version = "0.38.41"
+version = "0.38.44"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d7f649912bc1495e167a6edee79151c84b1bad49748cb4f1f1167f459f6224f6"
+checksum = "fdb5bc1ae2baa591800df16c9ca78619bf65c0488b41b96ccec5d11220d8c154"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.8.0",
  "errno",
  "libc",
  "linux-raw-sys",
- "windows-sys 0.52.0",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
@@ -3910,9 +3940,9 @@ dependencies = [
 
 [[package]]
 name = "rustls"
-version = "0.23.17"
+version = "0.23.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7f1a745511c54ba6d4465e8d5dfbd81b45791756de28d4981af70d6dca128f1e"
+checksum = "8f287924602bf649d949c63dc8ac8b235fa5387d394020705b80c4eb597ce5b8"
 dependencies = [
  "aws-lc-rs",
  "log",
@@ -3932,7 +3962,7 @@ dependencies = [
  "openssl-probe",
  "rustls-pki-types",
  "schannel",
- "security-framework 3.0.1",
+ "security-framework 3.2.0",
 ]
 
 [[package]]
@@ -3946,9 +3976,9 @@ dependencies = [
 
 [[package]]
 name = "rustls-pki-types"
-version = "1.10.0"
+version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "16f1201b3c9a7ee8039bcadc17b7e605e2945b27eee7631788c1bd2b0643674b"
+checksum = "917ce264624a4b4db1c364dcc35bfca9ded014d0a958cd47ad3e960e988ea51c"
 
 [[package]]
 name = "rustls-webpki"
@@ -3964,15 +3994,15 @@ dependencies = [
 
 [[package]]
 name = "rustversion"
-version = "1.0.18"
+version = "1.0.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0e819f2bc632f285be6d7cd36e25940d45b2391dd6d9b939e79de557f7014248"
+checksum = "f7c45b9784283f1b2e7fb61b42047c2fd678ef0960d4f6f1eba131594cc369d4"
 
 [[package]]
 name = "ryu"
-version = "1.0.18"
+version = "1.0.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f3cb5ba0dc43242ce17de99c180e96db90b235b8a9fdc9543c96d2209116bd9f"
+checksum = "6ea1a2d0a644769cc99faa24c3ad26b379b786fe7c36fd3c546254801650e6dd"
 
 [[package]]
 name = "same-file"
@@ -4020,7 +4050,7 @@ version = "2.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "897b2245f0b511c87893af39b033e5ca9cce68824c4d7e7630b5a1d339658d02"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.8.0",
  "core-foundation 0.9.4",
  "core-foundation-sys",
  "libc",
@@ -4029,11 +4059,11 @@ dependencies = [
 
 [[package]]
 name = "security-framework"
-version = "3.0.1"
+version = "3.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e1415a607e92bec364ea2cf9264646dcce0f91e6d65281bd6f2819cca3bf39c8"
+checksum = "271720403f46ca04f7ba6f55d438f8bd878d6b8ca0a1046e8228c4145bcbb316"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.8.0",
  "core-foundation 0.10.0",
  "core-foundation-sys",
  "libc",
@@ -4042,9 +4072,9 @@ dependencies = [
 
 [[package]]
 name = "security-framework-sys"
-version = "2.12.1"
+version = "2.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fa39c7303dc58b5543c94d22c1766b0d31f2ee58306363ea622b10bbc075eaa2"
+checksum = "49db231d56a190491cb4aeda9527f1ad45345af50b0851622a7adb8c03b01c32"
 dependencies = [
  "core-foundation-sys",
  "libc",
@@ -4052,18 +4082,18 @@ dependencies = [
 
 [[package]]
 name = "semver"
-version = "1.0.23"
+version = "1.0.25"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "61697e0a1c7e512e84a621326239844a24d8207b4669b41bc18b32ea5cbf988b"
+checksum = "f79dfe2d285b0488816f30e700a7438c5a73d816b5b7d3ac72fbc48b0d185e03"
 dependencies = [
  "serde",
 ]
 
 [[package]]
 name = "serde"
-version = "1.0.215"
+version = "1.0.217"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6513c1ad0b11a9376da888e3e0baa0077f1aed55c17f50e7b2397136129fb88f"
+checksum = "02fc4265df13d6fa1d00ecff087228cc0a2b5f3c0e87e258d8b94a156e984c70"
 dependencies = [
  "serde_derive",
 ]
@@ -4090,22 +4120,22 @@ dependencies = [
 
 [[package]]
 name = "serde_derive"
-version = "1.0.215"
+version = "1.0.217"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ad1e866f866923f252f05c889987993144fb74e722403468a4ebd70c3cd756c0"
+checksum = "5a9bf7cf98d04a2b28aead066b7496853d4779c9cc183c440dbac457641e19a0"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
 name = "serde_json"
-version = "1.0.133"
+version = "1.0.138"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c7fceb2473b9166b2294ef05efcb65a3db80803f0b03ef86a5fc88a2b85ee377"
+checksum = "d434192e7da787e94a6ea7e9670b26a036d0ca41e0b7efb2676dd32bae872949"
 dependencies = [
- "indexmap 2.6.0",
+ "indexmap 2.7.1",
  "itoa",
  "memchr",
  "ryu",
@@ -4246,9 +4276,9 @@ checksum = "3c5e1a9a646d36c3599cd173a41282daf47c44583ad367b8e6837255952e5c67"
 
 [[package]]
 name = "socket2"
-version = "0.5.7"
+version = "0.5.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ce305eb0b4296696835b71df73eb912e0f1ffd2556a501fcede6e0c50349191c"
+checksum = "c970269d99b64e60ec3bd6ad27270092a5394c4e309314b18ae3fe575695fbe8"
 dependencies = [
  "libc",
  "windows-sys 0.52.0",
@@ -4315,7 +4345,7 @@ dependencies = [
  "proc-macro2",
  "quote",
  "rustversion",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -4337,9 +4367,9 @@ dependencies = [
 
 [[package]]
 name = "syn"
-version = "2.0.89"
+version = "2.0.96"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "44d46482f1c1c87acd84dea20c1bf5ebff4c757009ed6bf19cfd36fb10e92c4e"
+checksum = "d5d0adab1ae378d7f53bdebc67a39f1f151407ef230f0ce2883572f5d8985c80"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -4369,7 +4399,7 @@ checksum = "c8af7666ab7b6390ab78131fb5b0fce11d6b7a6951602017c35fa82800708971"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -4453,12 +4483,13 @@ checksum = "61c41af27dd6d1e27b1b16b489db798443478cef1f06a660c96db617ba5de3b1"
 
 [[package]]
 name = "tempfile"
-version = "3.14.0"
+version = "3.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "28cce251fcbc87fac86a866eeb0d6c2d536fc16d06f184bb61aeae11aa4cee0c"
+checksum = "38c246215d7d24f48ae091a2902398798e05d978b24315d6efbc00ede9a8bb91"
 dependencies = [
  "cfg-if",
  "fastrand",
+ "getrandom 0.3.1",
  "once_cell",
  "rustix",
  "windows-sys 0.59.0",
@@ -4478,16 +4509,16 @@ name = "text-generation-backends-trtllm"
 version = "3.1.1-dev0"
 dependencies = [
  "async-trait",
- "clap 4.5.21",
+ "clap 4.5.27",
  "cmake",
  "cxx",
  "cxx-build",
- "hashbrown 0.15.1",
+ "hashbrown 0.15.2",
  "hf-hub",
  "pkg-config",
  "pyo3",
  "text-generation-router",
- "thiserror",
+ "thiserror 1.0.69",
  "tokenizers",
  "tokio",
  "tokio-stream",
@@ -4499,7 +4530,7 @@ name = "text-generation-benchmark"
 version = "3.1.1-dev0"
 dependencies = [
  "average",
- "clap 4.5.21",
+ "clap 4.5.27",
  "float-ord",
  "hf-hub",
  "ratatui",
@@ -4507,7 +4538,7 @@ dependencies = [
  "serde_json",
  "tabled",
  "text-generation-client",
- "thiserror",
+ "thiserror 1.0.69",
  "tokenizers",
  "tokio",
  "tracing",
@@ -4524,7 +4555,7 @@ dependencies = [
  "grpc-metadata",
  "prost 0.12.6",
  "prost-build",
- "thiserror",
+ "thiserror 1.0.69",
  "tokio",
  "tonic 0.10.2",
  "tonic-build",
@@ -4536,7 +4567,7 @@ dependencies = [
 name = "text-generation-launcher"
 version = "3.1.1-dev0"
 dependencies = [
- "clap 4.5.21",
+ "clap 4.5.27",
  "ctrlc",
  "float_eq",
  "hf-hub",
@@ -4547,7 +4578,7 @@ dependencies = [
  "reqwest 0.11.27",
  "serde",
  "serde_json",
- "thiserror",
+ "thiserror 1.0.69",
  "tracing",
  "tracing-subscriber",
  "vergen",
@@ -4564,7 +4595,7 @@ dependencies = [
  "axum-tracing-opentelemetry",
  "base64 0.22.1",
  "chrono",
- "clap 4.5.21",
+ "clap 4.5.27",
  "csv",
  "futures",
  "futures-util",
@@ -4590,7 +4621,7 @@ dependencies = [
  "serde",
  "serde_json",
  "sysinfo",
- "thiserror",
+ "thiserror 1.0.69",
  "tokenizers",
  "tokio",
  "tokio-stream",
@@ -4605,6 +4636,23 @@ dependencies = [
  "vergen",
 ]
 
+[[package]]
+name = "text-generation-router-llamacpp"
+version = "3.1.1-dev0"
+dependencies = [
+ "async-trait",
+ "bindgen 0.71.1",
+ "clap 4.5.27",
+ "num_cpus",
+ "pkg-config",
+ "text-generation-router",
+ "thiserror 2.0.11",
+ "tokenizers",
+ "tokio",
+ "tokio-stream",
+ "tracing",
+]
+
 [[package]]
 name = "text-generation-router-v2"
 version = "3.1.1-dev0"
@@ -4614,7 +4662,7 @@ dependencies = [
  "axum 0.7.9",
  "axum-tracing-opentelemetry",
  "base64 0.22.1",
- "clap 4.5.21",
+ "clap 4.5.27",
  "futures",
  "futures-util",
  "grpc-metadata",
@@ -4639,7 +4687,7 @@ dependencies = [
  "serde_json",
  "slotmap",
  "text-generation-router",
- "thiserror",
+ "thiserror 1.0.69",
  "tokenizers",
  "tokio",
  "tokio-stream",
@@ -4663,7 +4711,7 @@ dependencies = [
  "axum 0.7.9",
  "axum-tracing-opentelemetry",
  "base64 0.22.1",
- "clap 4.5.21",
+ "clap 4.5.27",
  "criterion",
  "futures",
  "futures-util",
@@ -4690,7 +4738,7 @@ dependencies = [
  "serde_json",
  "slotmap",
  "text-generation-router",
- "thiserror",
+ "thiserror 1.0.69",
  "tokenizers",
  "tokio",
  "tokio-stream",
@@ -4720,7 +4768,16 @@ version = "1.0.69"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b6aaf5339b578ea85b50e080feb250a3e8ae8cfcdff9a461c9ec2904bc923f52"
 dependencies = [
- "thiserror-impl",
+ "thiserror-impl 1.0.69",
+]
+
+[[package]]
+name = "thiserror"
+version = "2.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d452f284b73e6d76dd36758a0c8684b1d5be31f92b89d07fd5822175732206fc"
+dependencies = [
+ "thiserror-impl 2.0.11",
 ]
 
 [[package]]
@@ -4731,7 +4788,18 @@ checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "2.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "26afc1baea8a989337eeb52b6e72a039780ce45c3edfcc9c5b9d112feeb173c2"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -4757,9 +4825,9 @@ dependencies = [
 
 [[package]]
 name = "time"
-version = "0.3.36"
+version = "0.3.37"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5dfd88e563464686c916c7e46e623e520ddc6d79fa6641390f2e3fa86e83e885"
+checksum = "35e7868883861bd0e56d9ac6efcaaca0d6d5d82a2a7ec8209ff492c07cf37b21"
 dependencies = [
  "deranged",
  "itoa",
@@ -4780,9 +4848,9 @@ checksum = "ef927ca75afb808a4d64dd374f00a2adf8d0fcff8e7b184af886c3c87ec4a3f3"
 
 [[package]]
 name = "time-macros"
-version = "0.2.18"
+version = "0.2.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3f252a68540fde3a3877aeea552b832b40ab9a69e318efd078774a01ddee1ccf"
+checksum = "2834e6017e3e5e4b9834939793b282bc03b37a3336245fa820e35e233e2a85de"
 dependencies = [
  "num-conv",
  "time-core",
@@ -4810,14 +4878,14 @@ dependencies = [
 
 [[package]]
 name = "tokenizers"
-version = "0.20.3"
+version = "0.20.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "67b67c92f6d705e2a1d106fb0b28c696f9074901a9c656ee5d9f5de204c39bf7"
+checksum = "3b08cc37428a476fc9e20ac850132a513a2e1ce32b6a31addf2b74fa7033b905"
 dependencies = [
  "aho-corasick",
  "derive_builder",
  "esaxx-rs",
- "getrandom",
+ "getrandom 0.2.15",
  "hf-hub",
  "indicatif",
  "itertools 0.12.1",
@@ -4835,7 +4903,7 @@ dependencies = [
  "serde",
  "serde_json",
  "spm_precompiled",
- "thiserror",
+ "thiserror 1.0.69",
  "unicode-normalization-alignments",
  "unicode-segmentation",
  "unicode_categories",
@@ -4877,7 +4945,7 @@ checksum = "6e06d43f1345a3bcd39f6a56dbb7dcab2ba47e68e8ac134855e7e2bdbaf8cab8"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -4903,12 +4971,11 @@ dependencies = [
 
 [[package]]
 name = "tokio-rustls"
-version = "0.26.0"
+version = "0.26.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0c7bc40d0e5a97695bb96e27995cd3a08538541b0a846f65bba7a359f36700d4"
+checksum = "5f6d0975eaace0cf0fcadee4e4aaa5da15b5c079146f2cffb67c113be122bf37"
 dependencies = [
- "rustls 0.23.17",
- "rustls-pki-types",
+ "rustls 0.23.21",
  "tokio",
 ]
 
@@ -4925,9 +4992,9 @@ dependencies = [
 
 [[package]]
 name = "tokio-util"
-version = "0.7.12"
+version = "0.7.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "61e7c3654c13bcd040d4a03abee2c75b1d14a37b423cf5a813ceae1cc903ec6a"
+checksum = "d7fcaa8d55a2bdd6b83ace262b016eca0d79ee02818c5c1bcdf0305114081078"
 dependencies = [
  "bytes",
  "futures-core",
@@ -4964,7 +5031,7 @@ version = "0.22.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4ae48d6208a266e853d946088ed816055e556cc6028c5e8e2b84d9fa5dd7c7f5"
 dependencies = [
- "indexmap 2.6.0",
+ "indexmap 2.7.1",
  "serde",
  "serde_spanned",
  "toml_datetime",
@@ -4986,7 +5053,7 @@ dependencies = [
  "h2 0.3.26",
  "http 0.2.12",
  "http-body 0.4.6",
- "hyper 0.14.31",
+ "hyper 0.14.32",
  "hyper-timeout",
  "percent-encoding",
  "pin-project",
@@ -5013,7 +5080,7 @@ dependencies = [
  "h2 0.3.26",
  "http 0.2.12",
  "http-body 0.4.6",
- "hyper 0.14.31",
+ "hyper 0.14.32",
  "hyper-timeout",
  "percent-encoding",
  "pin-project",
@@ -5036,7 +5103,7 @@ dependencies = [
  "proc-macro2",
  "prost-build",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -5061,14 +5128,14 @@ dependencies = [
 
 [[package]]
 name = "tower"
-version = "0.5.1"
+version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2873938d487c3cfb9aed7546dc9f2711d867c9f90c46b889989a2cb84eba6b4f"
+checksum = "d039ad9159c98b70ecfd540b2573b97f7f52c3e8d9f8ad57a24b916a536975f9"
 dependencies = [
  "futures-core",
  "futures-util",
  "pin-project-lite",
- "sync_wrapper 0.1.2",
+ "sync_wrapper 1.0.2",
  "tokio",
  "tower-layer",
  "tower-service",
@@ -5081,9 +5148,9 @@ version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1e9cd434a998747dd2c4276bc96ee2e0c7a2eadf3cae88e52be55a05fa9053f5"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.8.0",
  "bytes",
- "http 1.1.0",
+ "http 1.2.0",
  "http-body 1.0.1",
  "http-body-util",
  "pin-project-lite",
@@ -5105,9 +5172,9 @@ checksum = "8df9b6e13f2d32c91b9bd719c00d1958837bc7dec474d94952798cc8e69eeec3"
 
 [[package]]
 name = "tracing"
-version = "0.1.40"
+version = "0.1.41"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c3523ab5a71916ccf420eebdf5521fcef02141234bbc0b8a49f2fdc4544364ef"
+checksum = "784e0ac535deb450455cbfa28a6f0df145ea1bb7ae51b821cf5e7927fdcfbdd0"
 dependencies = [
  "log",
  "pin-project-lite",
@@ -5117,20 +5184,20 @@ dependencies = [
 
 [[package]]
 name = "tracing-attributes"
-version = "0.1.27"
+version = "0.1.28"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "34704c8d6ebcbc939824180af020566b01a7c01f80641264eba0999f6c2b6be7"
+checksum = "395ae124c09f9e6918a2310af6038fba074bcf474ac352496d5910dd59a2226d"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
 name = "tracing-core"
-version = "0.1.32"
+version = "0.1.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c06d3da6113f116aaee68e4d601191614c9053067f9ab7f6edbcb161237daa54"
+checksum = "e672c95779cf947c5311f83787af4fa8fffd12fb27e4993211a84bdfd9610f9c"
 dependencies = [
  "once_cell",
  "valuable",
@@ -5198,7 +5265,7 @@ version = "0.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9920abb6a3ee3a2af7d30c9ff02900f8481935d36723c3da95cf807468218e8c"
 dependencies = [
- "http 1.1.0",
+ "http 1.2.0",
  "opentelemetry 0.21.0",
  "tracing",
  "tracing-opentelemetry 0.22.0",
@@ -5206,9 +5273,9 @@ dependencies = [
 
 [[package]]
 name = "tracing-serde"
-version = "0.1.3"
+version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bc6b213177105856957181934e4920de57730fc69bf42c37ee5bb664d406d9e1"
+checksum = "704b1aeb7be0d0a84fc9828cae51dab5970fee5088f83d1dd7ee6f6246fc6ff1"
 dependencies = [
  "serde",
  "tracing-core",
@@ -5216,9 +5283,9 @@ dependencies = [
 
 [[package]]
 name = "tracing-subscriber"
-version = "0.3.18"
+version = "0.3.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ad0f048c97dbd9faa9b7df56362b8ebcaa52adb06b498c050d2f4e32f90a7a8b"
+checksum = "e8189decb5ac0fa7bc8b96b7cb9b2701d60d48805aca84a238004d665fcc4008"
 dependencies = [
  "matchers",
  "nu-ansi-term",
@@ -5249,15 +5316,15 @@ checksum = "42ff0bf0c66b8238c6f3b578df37d0b7848e55df8577b3f74f92a69acceeb825"
 
 [[package]]
 name = "unicase"
-version = "2.8.0"
+version = "2.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7e51b68083f157f853b6379db119d1c1be0e6e4dec98101079dec41f6f5cf6df"
+checksum = "75b844d17643ee918803943289730bec8aac480150456169e647ed0b576ba539"
 
 [[package]]
 name = "unicode-ident"
-version = "1.0.14"
+version = "1.0.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "adb9e6ca4f869e1180728b7950e35922a7fc6397f7b641499e8f3ef06e50dc83"
+checksum = "a210d160f08b701c8721ba1c726c11662f877ea6b7094007e1ca9a1041945034"
 
 [[package]]
 name = "unicode-normalization-alignments"
@@ -5343,9 +5410,9 @@ dependencies = [
 
 [[package]]
 name = "url"
-version = "2.5.3"
+version = "2.5.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8d157f1b96d14500ffdc1f10ba712e780825526c03d9a49b4d0324b0d9113ada"
+checksum = "32f8b686cadd1473f4bd0117a5d28d36b1ade384ea9b5069a1c40aefed7fda60"
 dependencies = [
  "form_urlencoded",
  "idna",
@@ -5382,7 +5449,7 @@ version = "4.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c5afb1a60e207dca502682537fefcfd9921e71d0b83e9576060f09abc6efab23"
 dependencies = [
- "indexmap 2.6.0",
+ "indexmap 2.7.1",
  "serde",
  "serde_json",
  "utoipa-gen",
@@ -5398,7 +5465,7 @@ dependencies = [
  "proc-macro2",
  "quote",
  "regex",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -5419,24 +5486,24 @@ dependencies = [
 
 [[package]]
 name = "uuid"
-version = "1.11.0"
+version = "1.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f8c5f0a0af699448548ad1a2fbf920fb4bee257eae39953ba95cb84891a0446a"
+checksum = "b3758f5e68192bb96cc8f9b7e2c2cfdabb435499a28499a42f8f984092adad4b"
 dependencies = [
- "getrandom",
+ "getrandom 0.2.15",
  "rand",
  "uuid-macro-internal",
 ]
 
 [[package]]
 name = "uuid-macro-internal"
-version = "1.11.0"
+version = "1.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6b91f57fe13a38d0ce9e28a03463d8d3c2468ed03d75375110ec71d93b449a08"
+checksum = "f8a86d88347b61a0e17b9908a67efcc594130830bf1045653784358dd023e294"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -5463,9 +5530,9 @@ dependencies = [
 
 [[package]]
 name = "valuable"
-version = "0.1.0"
+version = "0.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "830b7e5d4d90034032940e4ace0d9a9a057e7a45cd94e6c007832e39edb82f6d"
+checksum = "ba73ea9cf16a25df0c8caa16c51acb937d5712a8429db78a3ee29d5dcacd3a65"
 
 [[package]]
 name = "vcpkg"
@@ -5532,49 +5599,59 @@ version = "0.11.0+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
 
+[[package]]
+name = "wasi"
+version = "0.13.3+wasi-0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "26816d2e1a4a36a2940b96c5296ce403917633dff8f3440e9b236ed6f6bacad2"
+dependencies = [
+ "wit-bindgen-rt",
+]
+
 [[package]]
 name = "wasm-bindgen"
-version = "0.2.95"
+version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "128d1e363af62632b8eb57219c8fd7877144af57558fb2ef0368d0087bddeb2e"
+checksum = "1edc8929d7499fc4e8f0be2262a241556cfc54a0bea223790e71446f2aab1ef5"
 dependencies = [
  "cfg-if",
  "once_cell",
+ "rustversion",
  "wasm-bindgen-macro",
 ]
 
 [[package]]
 name = "wasm-bindgen-backend"
-version = "0.2.95"
+version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cb6dd4d3ca0ddffd1dd1c9c04f94b868c37ff5fac97c30b97cff2d74fce3a358"
+checksum = "2f0a0651a5c2bc21487bde11ee802ccaf4c51935d0d3d42a6101f98161700bc6"
 dependencies = [
  "bumpalo",
  "log",
- "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
  "wasm-bindgen-shared",
 ]
 
 [[package]]
 name = "wasm-bindgen-futures"
-version = "0.4.45"
+version = "0.4.50"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cc7ec4f8827a71586374db3e87abdb5a2bb3a15afed140221307c3ec06b1f63b"
+checksum = "555d470ec0bc3bb57890405e5d4322cc9ea83cebb085523ced7be4144dac1e61"
 dependencies = [
  "cfg-if",
  "js-sys",
+ "once_cell",
  "wasm-bindgen",
  "web-sys",
 ]
 
 [[package]]
 name = "wasm-bindgen-macro"
-version = "0.2.95"
+version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e79384be7f8f5a9dd5d7167216f022090cf1f9ec128e6e6a482a2cb5c5422c56"
+checksum = "7fe63fc6d09ed3792bd0897b314f53de8e16568c2b3f7982f468c0bf9bd0b407"
 dependencies = [
  "quote",
  "wasm-bindgen-macro-support",
@@ -5582,28 +5659,31 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro-support"
-version = "0.2.95"
+version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "26c6ab57572f7a24a4985830b120de1594465e5d500f24afe89e16b4e833ef68"
+checksum = "8ae87ea40c9f689fc23f209965b6fb8a99ad69aeeb0231408be24920604395de"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
  "wasm-bindgen-backend",
  "wasm-bindgen-shared",
 ]
 
 [[package]]
 name = "wasm-bindgen-shared"
-version = "0.2.95"
+version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "65fc09f10666a9f147042251e0dda9c18f166ff7de300607007e96bdebc1068d"
+checksum = "1a05d73b933a847d6cccdda8f838a22ff101ad9bf93e33684f39c1f5f0eece3d"
+dependencies = [
+ "unicode-ident",
+]
 
 [[package]]
 name = "web-sys"
-version = "0.3.72"
+version = "0.3.77"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f6488b90108c040df0fe62fa815cbdee25124641df01814dd7282749234c6112"
+checksum = "33b6dd2ef9186f1f2072e409e99cd22a975331a6b3591b12c764e0e55c60d5d2"
 dependencies = [
  "js-sys",
  "wasm-bindgen",
@@ -5962,9 +6042,9 @@ checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
 
 [[package]]
 name = "winnow"
-version = "0.6.20"
+version = "0.6.25"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "36c1fec1a2bb5866f07c25f68c26e565c4c200aebb96d7e55710c19d3e8ac49b"
+checksum = "ad699df48212c6cc6eb4435f35500ac6fd3b9913324f938aea302022ce19d310"
 dependencies = [
  "memchr",
 ]
@@ -5979,6 +6059,15 @@ dependencies = [
  "windows-sys 0.48.0",
 ]
 
+[[package]]
+name = "wit-bindgen-rt"
+version = "0.33.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3268f3d866458b787f390cf61f4bbb563b922d091359f9608842999eaee3943c"
+dependencies = [
+ "bitflags 2.8.0",
+]
+
 [[package]]
 name = "write16"
 version = "1.0.0"
@@ -5991,17 +6080,11 @@ version = "0.5.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1e9df38ee2d2c3c5948ea468a8406ff0db0b29ae1ffde1bcf20ef305bcc95c51"
 
-[[package]]
-name = "yansi"
-version = "1.0.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cfe53a6657fd280eaa890a3bc59152892ffa3e30101319d168b781ed6529b049"
-
 [[package]]
 name = "yoke"
-version = "0.7.4"
+version = "0.7.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6c5b1314b079b0930c31e3af543d8ee1757b1951ae1e1565ec704403a7240ca5"
+checksum = "120e6aef9aa629e3d4f52dc8cc43a015c7724194c97dfaf45180d2daf2b77f40"
 dependencies = [
  "serde",
  "stable_deref_trait",
@@ -6011,13 +6094,13 @@ dependencies = [
 
 [[package]]
 name = "yoke-derive"
-version = "0.7.4"
+version = "0.7.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "28cc31741b18cb6f1d5ff12f5b7523e3d6eb0852bbbad19d73905511d9849b95"
+checksum = "2380878cad4ac9aac1e2435f3eb4020e8374b5f13c296cb75b4620ff8e229154"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
  "synstructure",
 ]
 
@@ -6039,27 +6122,27 @@ checksum = "fa4f8080344d4671fb4e831a13ad1e68092748387dfc4f55e356242fae12ce3e"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
 name = "zerofrom"
-version = "0.1.4"
+version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "91ec111ce797d0e0784a1116d0ddcdbea84322cd79e5d5ad173daeba4f93ab55"
+checksum = "cff3ee08c995dee1859d998dea82f7374f2826091dd9cd47def953cae446cd2e"
 dependencies = [
  "zerofrom-derive",
 ]
 
 [[package]]
 name = "zerofrom-derive"
-version = "0.1.4"
+version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0ea7b4a3637ea8669cedf0f1fd5c286a17f3de97b8dd5a70a6c167a1730e63a5"
+checksum = "595eed982f7d355beb85837f651fa22e90b3c044842dc7f2c2842c086f295808"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
  "synstructure",
 ]
 
@@ -6088,7 +6171,7 @@ checksum = "6eafa6dfb17584ea3e2bd6e76e0cc15ad7af12b09abdd1ca55961bed9b1063c6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.89",
+ "syn 2.0.96",
 ]
 
 [[package]]
@@ -6120,9 +6203,9 @@ dependencies = [
 
 [[package]]
 name = "zune-jpeg"
-version = "0.4.13"
+version = "0.4.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "16099418600b4d8f028622f73ff6e3deaabdff330fb9a2a131dea781ee8b0768"
+checksum = "99a5bab8d7dedf81405c4bb1f2b83ea057643d9cb28778cea9eecddeedd2e028"
 dependencies = [
  "zune-core",
 ]
diff --git a/Cargo.toml b/Cargo.toml
index 6fd4b51d7e4..df7f2a73e56 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -5,6 +5,7 @@ members = [
     "backends/v3",
     "backends/grpc-metadata",
     "backends/trtllm",
+    "backends/llamacpp",
     "launcher",
     "router"
 ]
diff --git a/Dockerfile_llamacpp b/Dockerfile_llamacpp
new file mode 100644
index 00000000000..2eb62a1f66c
--- /dev/null
+++ b/Dockerfile_llamacpp
@@ -0,0 +1,76 @@
+FROM nvidia/cuda:12.8.0-cudnn-devel-ubuntu24.04 AS deps
+
+ARG llamacpp_version=b4651
+ARG llamacpp_cuda=OFF
+ARG cuda_arch=75-real;80-real;86-real;89-real;90-real
+
+WORKDIR /opt/src
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN apt update && apt install -y \
+    clang \
+    cmake \
+    curl \
+    git \
+    python3-dev \
+    libssl-dev \
+    pkg-config \
+    tar
+
+ADD https://github.com/ggerganov/llama.cpp/archive/refs/tags/${llamacpp_version}.tar.gz /opt/src/
+RUN tar -xzf ${llamacpp_version}.tar.gz \
+ && cd llama.cpp-${llamacpp_version} \
+ && cmake -B build \
+    -DCMAKE_INSTALL_PREFIX=/usr \
+    -DCMAKE_INSTALL_LIBDIR=/usr/lib \
+    -DCMAKE_C_COMPILER=clang \
+    -DCMAKE_CXX_COMPILER=clang++ \
+    -DCMAKE_CUDA_ARCHITECTURES=${cuda_arch} \
+    -DGGML_CUDA=${llamacpp_cuda} \
+    -DLLAMA_BUILD_COMMON=OFF \
+    -DLLAMA_BUILD_TESTS=OFF \
+    -DLLAMA_BUILD_EXAMPLES=OFF \
+    -DLLAMA_BUILD_SERVER=OFF \
+ && cmake --build build --parallel --config Release \
+ && cmake --install build
+
+WORKDIR /app
+COPY rust-toolchain.toml rust-toolchain.toml
+RUN curl -sSf https://sh.rustup.rs | sh -s -- -y --no-modify-path --default-toolchain none
+ENV PATH="/root/.cargo/bin:$PATH"
+RUN cargo install cargo-chef --locked
+
+FROM deps AS planner
+COPY . .
+RUN cargo chef prepare --recipe-path recipe.json
+
+FROM deps AS builder
+COPY --from=planner /app/recipe.json recipe.json
+RUN cargo chef cook \
+    --recipe-path recipe.json \
+    --profile release-opt \
+    --package text-generation-router-llamacpp
+COPY . .
+RUN cargo build \
+    --profile release-opt \
+    --package text-generation-router-llamacpp --frozen
+
+FROM nvidia/cuda:12.8.0-cudnn-runtime-ubuntu24.04
+
+RUN apt update && apt install -y \
+    python3-venv \
+    python3-pip
+
+RUN python3 -m venv /venv
+ENV PATH="/venv/bin:$PATH"
+
+COPY backends/llamacpp/requirements.txt requirements.txt
+RUN pip3 install --no-cache-dir -r requirements.txt
+
+COPY --from=builder /usr/lib/libllama.so /usr/lib/
+COPY --from=builder /usr/lib/libggml*.so /usr/lib/
+COPY --from=builder /app/target/release-opt/text-generation-router-llamacpp /usr/bin/
+
+ENV HF_HUB_ENABLE_HF_TRANSFER=1
+
+ENTRYPOINT ["text-generation-router-llamacpp"]
diff --git a/backends/llamacpp/Cargo.toml b/backends/llamacpp/Cargo.toml
new file mode 100644
index 00000000000..18c2ed0a80b
--- /dev/null
+++ b/backends/llamacpp/Cargo.toml
@@ -0,0 +1,21 @@
+[package]
+name = "text-generation-router-llamacpp"
+version.workspace = true
+edition.workspace = true
+authors.workspace = true
+homepage.workspace = true
+
+[build-dependencies]
+bindgen = "0.71.1"
+pkg-config = "0.3.31"
+
+[dependencies]
+async-trait = "0.1.85"
+clap = "4.5.27"
+num_cpus = "1.16.0"
+text-generation-router = { path = "../../router" }
+thiserror = "2.0.11"
+tokenizers.workspace = true
+tokio = "1.43.0"
+tokio-stream = "0.1.17"
+tracing = "0.1.41"
diff --git a/backends/llamacpp/README.md b/backends/llamacpp/README.md
new file mode 100644
index 00000000000..0971efc5a39
--- /dev/null
+++ b/backends/llamacpp/README.md
@@ -0,0 +1,24 @@
+# Llamacpp backend
+
+If all your dependencies are installed at the system level, running
+cargo build should be sufficient. However, if you want to experiment
+with different versions of llama.cpp, some additional setup is required.
+
+## Install llama.cpp
+
+    LLAMACPP_PREFIX=$(pwd)/llama.cpp.out
+
+    git clone https://github.com/ggerganov/llama.cpp
+    cd llama.cpp
+    cmake -B build \
+        -DCMAKE_INSTALL_PREFIX="$LLAMACPP_PREFIX" \
+        -DLLAMA_BUILD_COMMON=OFF \
+        -DLLAMA_BUILD_TESTS=OFF \
+        -DLLAMA_BUILD_EXAMPLES=OFF \
+        -DLLAMA_BUILD_SERVER=OFF
+    cmake --build build --config Release -j
+    cmake --install build
+
+## Build TGI
+
+    PKG_CONFIG_PATH="$LLAMACPP_PREFIX/lib/pkgconfig" cargo build
diff --git a/backends/llamacpp/build.rs b/backends/llamacpp/build.rs
new file mode 100644
index 00000000000..499583cd445
--- /dev/null
+++ b/backends/llamacpp/build.rs
@@ -0,0 +1,48 @@
+use bindgen::callbacks::{ItemInfo, ParseCallbacks};
+use std::env;
+use std::path::PathBuf;
+
+#[derive(Debug)]
+struct PrefixStripper;
+
+impl ParseCallbacks for PrefixStripper {
+    fn generated_name_override(&self, item_info: ItemInfo<'_>) -> Option<String> {
+        item_info.name.strip_prefix("llama_").map(str::to_string)
+    }
+}
+
+fn main() {
+    if let Some(cuda_version) = option_env!("CUDA_VERSION") {
+        let mut version: Vec<&str> = cuda_version.split('.').collect();
+        if version.len() > 2 {
+            version.pop();
+        }
+        let cuda_version = format!("cuda-{}", version.join("."));
+        pkg_config::Config::new().probe(&cuda_version).unwrap();
+    }
+    let llama = pkg_config::Config::new().probe("llama").unwrap();
+
+    for path in &llama.link_paths {
+        println!("cargo:rustc-link-arg=-Wl,-rpath,{}", path.display());
+    }
+    println!("cargo:rustc-link-arg=-Wl,--disable-new-dtags");
+
+    let bindings = bindgen::Builder::default()
+        .clang_args(
+            llama
+                .include_paths
+                .iter()
+                .map(|p| format!("-I{}", p.display())),
+        )
+        .header_contents("llama_bindings.h", "#include <llama.h>")
+        .prepend_enum_name(false)
+        .parse_callbacks(Box::new(PrefixStripper))
+        .parse_callbacks(Box::new(bindgen::CargoCallbacks::new()))
+        .generate()
+        .expect("Unable to generate bindings");
+
+    let out_path = PathBuf::from(env::var("OUT_DIR").unwrap());
+    bindings
+        .write_to_file(out_path.join("llamacpp.rs"))
+        .expect("Couldn't write bindings!");
+}
diff --git a/backends/llamacpp/requirements.txt b/backends/llamacpp/requirements.txt
new file mode 100644
index 00000000000..5c5d0cc7f11
--- /dev/null
+++ b/backends/llamacpp/requirements.txt
@@ -0,0 +1,3 @@
+transformers==4.48.2
+huggingface-hub==0.28.1
+hf-transfer==0.1.9
diff --git a/backends/llamacpp/src/backend.rs b/backends/llamacpp/src/backend.rs
new file mode 100644
index 00000000000..1566e1bf968
--- /dev/null
+++ b/backends/llamacpp/src/backend.rs
@@ -0,0 +1,679 @@
+mod llamacpp {
+    #![allow(non_upper_case_globals)]
+    #![allow(non_camel_case_types)]
+    #![allow(non_snake_case)]
+    #![allow(dead_code)]
+    include!(concat!(env!("OUT_DIR"), "/llamacpp.rs"));
+}
+use async_trait::async_trait;
+use std::ffi::CString;
+use std::mem::replace;
+use std::str::FromStr;
+use std::sync::{mpsc, Once};
+use text_generation_router::infer::{Backend, GeneratedText, InferError, InferStreamResponse};
+use text_generation_router::validation::ValidGenerateRequest;
+use text_generation_router::{FinishReason, Token};
+use thiserror::Error;
+use tokenizers::Tokenizer;
+use tokio::sync::mpsc::{unbounded_channel, UnboundedSender};
+use tokio::sync::{oneshot, watch};
+use tokio::task::{spawn, spawn_blocking};
+use tokio::time::{timeout, Duration, Instant};
+use tokio_stream::wrappers::UnboundedReceiverStream;
+use tracing::instrument;
+use tracing::{debug, error, info, trace, warn};
+
+#[derive(Debug, Clone, Copy)]
+pub enum LlamacppSplitMode {
+    GPU(usize),
+    Layer,
+    Row,
+}
+
+impl FromStr for LlamacppSplitMode {
+    type Err = String;
+    fn from_str(s: &str) -> Result<Self, Self::Err> {
+        match s.to_lowercase().as_str() {
+            "layer" => Ok(LlamacppSplitMode::Layer),
+            "row" => Ok(LlamacppSplitMode::Row),
+            _ => match s.parse::<usize>() {
+                Ok(n) => Ok(LlamacppSplitMode::GPU(n)),
+                Err(_) => Err("Choose a GPU number or `layer` or `row`".to_string()),
+            },
+        }
+    }
+}
+
+#[derive(Debug, Clone, Copy, clap::ValueEnum)]
+pub enum LlamacppNuma {
+    Disabled,
+    Distribute,
+    Isolate,
+    Numactl,
+    Mirror,
+}
+
+#[allow(non_camel_case_types)]
+#[derive(Debug, Clone, Copy, clap::ValueEnum)]
+pub enum LlamacppGGMLType {
+    F32,
+    F16,
+    Q4_0,
+    Q4_1,
+    Q5_0,
+    Q5_1,
+    Q8_0,
+    Q8_1,
+    Q2_K,
+    Q3_K,
+    Q4_K,
+    Q5_K,
+    Q6_K,
+    Q8_K,
+    IQ2_XXS,
+    IQ2_XS,
+    IQ3_XXS,
+    IQ1_S,
+    IQ4_NL,
+    IQ3_S,
+    IQ2_S,
+    IQ4_XS,
+    I8,
+    I16,
+    I32,
+    I64,
+    F64,
+    IQ1_M,
+    BF16,
+    TQ1_0,
+    TQ2_0,
+}
+
+// TODO: macro
+impl LlamacppGGMLType {
+    fn to_ggml_type(self) -> llamacpp::ggml_type {
+        match self {
+            LlamacppGGMLType::F32 => llamacpp::GGML_TYPE_F32,
+            LlamacppGGMLType::F16 => llamacpp::GGML_TYPE_F16,
+            LlamacppGGMLType::Q4_0 => llamacpp::GGML_TYPE_Q4_0,
+            LlamacppGGMLType::Q4_1 => llamacpp::GGML_TYPE_Q4_1,
+            LlamacppGGMLType::Q5_0 => llamacpp::GGML_TYPE_Q5_0,
+            LlamacppGGMLType::Q5_1 => llamacpp::GGML_TYPE_Q5_1,
+            LlamacppGGMLType::Q8_0 => llamacpp::GGML_TYPE_Q8_0,
+            LlamacppGGMLType::Q8_1 => llamacpp::GGML_TYPE_Q8_1,
+            LlamacppGGMLType::Q2_K => llamacpp::GGML_TYPE_Q2_K,
+            LlamacppGGMLType::Q3_K => llamacpp::GGML_TYPE_Q3_K,
+            LlamacppGGMLType::Q4_K => llamacpp::GGML_TYPE_Q4_K,
+            LlamacppGGMLType::Q5_K => llamacpp::GGML_TYPE_Q5_K,
+            LlamacppGGMLType::Q6_K => llamacpp::GGML_TYPE_Q6_K,
+            LlamacppGGMLType::Q8_K => llamacpp::GGML_TYPE_Q8_K,
+            LlamacppGGMLType::IQ2_XXS => llamacpp::GGML_TYPE_IQ2_XXS,
+            LlamacppGGMLType::IQ2_XS => llamacpp::GGML_TYPE_IQ2_XS,
+            LlamacppGGMLType::IQ3_XXS => llamacpp::GGML_TYPE_IQ3_XXS,
+            LlamacppGGMLType::IQ1_S => llamacpp::GGML_TYPE_IQ1_S,
+            LlamacppGGMLType::IQ4_NL => llamacpp::GGML_TYPE_IQ4_NL,
+            LlamacppGGMLType::IQ3_S => llamacpp::GGML_TYPE_IQ3_S,
+            LlamacppGGMLType::IQ2_S => llamacpp::GGML_TYPE_IQ2_S,
+            LlamacppGGMLType::IQ4_XS => llamacpp::GGML_TYPE_IQ4_XS,
+            LlamacppGGMLType::I8 => llamacpp::GGML_TYPE_I8,
+            LlamacppGGMLType::I16 => llamacpp::GGML_TYPE_I16,
+            LlamacppGGMLType::I32 => llamacpp::GGML_TYPE_I32,
+            LlamacppGGMLType::I64 => llamacpp::GGML_TYPE_I64,
+            LlamacppGGMLType::F64 => llamacpp::GGML_TYPE_F64,
+            LlamacppGGMLType::IQ1_M => llamacpp::GGML_TYPE_IQ1_M,
+            LlamacppGGMLType::BF16 => llamacpp::GGML_TYPE_BF16,
+            LlamacppGGMLType::TQ1_0 => llamacpp::GGML_TYPE_TQ1_0,
+            LlamacppGGMLType::TQ2_0 => llamacpp::GGML_TYPE_TQ2_0,
+        }
+    }
+}
+
+pub struct LlamacppConfig {
+    pub model_gguf: String,
+    pub max_batch_total_tokens: usize,
+    pub max_physical_batch_total_tokens: usize,
+    pub max_batch_size: usize,
+    pub batch_timeout: Duration,
+    pub n_threads: usize,
+    pub n_threads_batch: usize,
+    pub n_gpu_layers: usize,
+    pub split_mode: LlamacppSplitMode,
+    pub numa: LlamacppNuma,
+    pub defrag_threshold: f32,
+    pub use_mmap: bool,
+    pub use_mlock: bool,
+    pub offload_kqv: bool,
+    pub flash_attention: bool,
+    pub type_k: LlamacppGGMLType,
+    pub type_v: LlamacppGGMLType,
+}
+
+#[derive(Debug)]
+struct LlamacppRequest {
+    input_ids: Vec<i32>,
+    top_k: i32,
+    top_p: f32,
+    typical_p: f32,
+    min_keep: usize,
+    temp: f32,
+    seed: u32,
+    penalty_last_n: i32,
+    penalty_repeat: f32,
+    penalty_freq: f32,
+    penalty_present: f32,
+    max_new_tokens: usize,
+    tx: UnboundedSender<Result<InferStreamResponse, InferError>>,
+    time: Instant,
+}
+
+pub struct LlamacppBackend {
+    tx: UnboundedSender<LlamacppRequest>,
+    status: watch::Receiver<bool>,
+}
+
+impl LlamacppRequest {
+    fn new(
+        from: &ValidGenerateRequest,
+        tx: UnboundedSender<Result<InferStreamResponse, InferError>>,
+    ) -> Option<Self> {
+        from.input_ids.as_ref().map(|input_ids| LlamacppRequest {
+            input_ids: input_ids.iter().map(|&x| x as i32).collect(),
+            top_k: from.parameters.top_k as _,
+            top_p: from.parameters.top_p as _,
+            typical_p: from.parameters.typical_p as _,
+            min_keep: 0, // disabled
+            temp: from.parameters.temperature as _,
+            seed: from.parameters.seed as _,
+            penalty_last_n: 64, // 0 = disabled, -1 = context size
+            penalty_repeat: from.parameters.repetition_penalty as _,
+            penalty_freq: from.parameters.frequency_penalty as _,
+            penalty_present: 0.0, // disabled
+            max_new_tokens: from.stopping_parameters.max_new_tokens as _,
+            tx,
+            time: Instant::now(),
+        })
+    }
+}
+
+struct Llamacpp {
+    model: *mut llamacpp::llama_model,
+    ctx: *mut llamacpp::llama_context,
+    vocab: *const llamacpp::llama_vocab,
+    logprobs: Vec<llamacpp::llama_token_data>,
+    batch: llamacpp::llama_batch,
+}
+
+extern "C" fn llamacpp_log_callback(
+    level: llamacpp::ggml_log_level,
+    msg: *const std::os::raw::c_char,
+    _user_data: *mut std::os::raw::c_void,
+) {
+    let cmsg = unsafe { std::ffi::CStr::from_ptr(msg) };
+    let rmsg = cmsg.to_string_lossy().trim_end_matches('\n').to_string();
+
+    match level {
+        llamacpp::GGML_LOG_LEVEL_DEBUG => debug!(target: "llamacpp", "{}", rmsg),
+        llamacpp::GGML_LOG_LEVEL_INFO => info!(target: "llamacpp", "{}", rmsg),
+        llamacpp::GGML_LOG_LEVEL_WARN => warn!(target: "llamacpp", "{}", rmsg),
+        llamacpp::GGML_LOG_LEVEL_ERROR => error!(target: "llamacpp", "{}", rmsg),
+        _ => trace!(target: "llamacpp", "{}", rmsg),
+    }
+}
+
+impl Llamacpp {
+    fn new(conf: LlamacppConfig) -> Result<Self, BackendError> {
+        let gguf = CString::new(conf.model_gguf)?;
+
+        let model = unsafe {
+            let mut params = llamacpp::model_default_params();
+            params.n_gpu_layers = conf.n_gpu_layers as _;
+            params.split_mode = match conf.split_mode {
+                LlamacppSplitMode::GPU(_) => llamacpp::LLAMA_SPLIT_MODE_NONE,
+                LlamacppSplitMode::Layer => llamacpp::LLAMA_SPLIT_MODE_LAYER,
+                LlamacppSplitMode::Row => llamacpp::LLAMA_SPLIT_MODE_ROW,
+            };
+            params.main_gpu = match conf.split_mode {
+                LlamacppSplitMode::GPU(n) => n as _,
+                _ => 0,
+            };
+            params.use_mmap = conf.use_mmap;
+            params.use_mlock = conf.use_mlock;
+            llamacpp::model_load_from_file(gguf.as_ptr(), params)
+        };
+        if model.is_null() {
+            return Err(BackendError::Llamacpp("Failed to load model".to_string()));
+        }
+        let ctx = unsafe {
+            let mut params = llamacpp::context_default_params();
+            params.n_ctx = conf.max_batch_total_tokens as _;
+            params.n_batch = conf.max_batch_total_tokens as _;
+            params.n_ubatch = conf.max_physical_batch_total_tokens as _;
+            params.n_seq_max = conf.max_batch_size as _;
+            params.n_threads = conf.n_threads as _;
+            params.n_threads_batch = conf.n_threads_batch as _;
+            params.defrag_thold = conf.defrag_threshold;
+            params.offload_kqv = conf.offload_kqv;
+            params.flash_attn = conf.flash_attention;
+            params.type_k = conf.type_k.to_ggml_type();
+            params.type_v = conf.type_v.to_ggml_type();
+            params.no_perf = true;
+            llamacpp::init_from_model(model, params)
+        };
+        if ctx.is_null() {
+            return Err(BackendError::Llamacpp("Failed to init context".to_string()));
+        }
+        let vocab = unsafe { llamacpp::model_get_vocab(model) };
+        if vocab.is_null() {
+            return Err(BackendError::Llamacpp("Failed to get vocab".to_string()));
+        }
+        let n_tokens = unsafe { llamacpp::vocab_n_tokens(vocab) };
+        let mut logprobs = Vec::with_capacity(n_tokens as usize);
+
+        for token in 0..n_tokens {
+            logprobs.push(llamacpp::llama_token_data {
+                id: token,
+                logit: 0.0,
+                p: 0.0,
+            });
+        }
+        let batch = unsafe { llamacpp::batch_init(conf.max_batch_total_tokens as _, 0, 1) };
+        Ok(Llamacpp {
+            model,
+            ctx,
+            vocab,
+            logprobs,
+            batch,
+        })
+    }
+
+    fn decode(&mut self) -> i32 {
+        unsafe { llamacpp::decode(self.ctx, self.batch) }
+    }
+
+    fn clear_kv_cache(&mut self, seq_id: llamacpp::llama_seq_id) {
+        unsafe {
+            llamacpp::kv_cache_seq_rm(self.ctx, seq_id, -1, -1);
+        }
+    }
+
+    fn batch_push(
+        &mut self,
+        token: llamacpp::llama_token,
+        pos: llamacpp::llama_pos,
+        seq_id: llamacpp::llama_seq_id,
+        logits: bool,
+    ) -> usize {
+        let n = self.batch.n_tokens as usize;
+        unsafe {
+            *self.batch.token.add(n) = token;
+            *self.batch.pos.add(n) = pos;
+            *self.batch.n_seq_id.add(n) = 1;
+            *(*self.batch.seq_id.add(n)).add(0) = seq_id;
+            *self.batch.logits.add(n) = logits as i8;
+        }
+        self.batch.n_tokens += 1;
+        n
+    }
+}
+
+impl Drop for Llamacpp {
+    fn drop(&mut self) {
+        if !self.ctx.is_null() {
+            unsafe { llamacpp::free(self.ctx) };
+        }
+        if !self.model.is_null() {
+            unsafe { llamacpp::model_free(self.model) };
+        }
+        unsafe { llamacpp::batch_free(self.batch) };
+    }
+}
+
+struct LlamacppSampler {
+    chain: *mut llamacpp::llama_sampler,
+}
+
+impl LlamacppSampler {
+    fn new(req: &LlamacppRequest) -> Option<Self> {
+        let chain = unsafe {
+            let params = llamacpp::sampler_chain_default_params();
+            llamacpp::sampler_chain_init(params)
+        };
+        if chain.is_null() {
+            error!("Failed to init sampler");
+            return None;
+        }
+        let (top_k, top_p, typical_p, temp, penalties, dist) = unsafe {
+            (
+                llamacpp::sampler_init_top_k(req.top_k),
+                llamacpp::sampler_init_top_p(req.top_p, req.min_keep),
+                llamacpp::sampler_init_typical(req.typical_p, req.min_keep),
+                llamacpp::sampler_init_temp(req.temp),
+                llamacpp::sampler_init_penalties(
+                    req.penalty_last_n,
+                    req.penalty_repeat,
+                    req.penalty_freq,
+                    req.penalty_present,
+                ),
+                llamacpp::sampler_init_dist(req.seed),
+            )
+        };
+        let all = &[
+            ("top_k", top_k),
+            ("top_p", top_p),
+            ("typical_p", typical_p),
+            ("temp", temp),
+            ("penalties", penalties),
+            ("dist", dist),
+        ];
+        let mut failed = false;
+
+        for (k, v) in all {
+            if v.is_null() {
+                error!("Failed to init {k} sampler");
+                failed = true;
+            } else {
+                unsafe { llamacpp::sampler_chain_add(chain, *v) };
+            }
+        }
+        if failed {
+            unsafe { llamacpp::sampler_free(chain) };
+            None
+        } else {
+            Some(LlamacppSampler { chain })
+        }
+    }
+
+    fn sample(&self, llamacpp: &mut Llamacpp, idx: usize) -> (llamacpp::llama_token, f32) {
+        let logits = unsafe { llamacpp::get_logits_ith(llamacpp.ctx, idx as _) };
+        for (token, logprob) in llamacpp.logprobs.iter_mut().enumerate() {
+            *logprob = llamacpp::llama_token_data {
+                id: token as _,
+                logit: unsafe { *logits.add(token) },
+                p: 0.0,
+            };
+        }
+        let mut view = llamacpp::llama_token_data_array {
+            data: llamacpp.logprobs.as_mut_ptr(),
+            size: llamacpp.logprobs.len(),
+            selected: -1,
+            sorted: false,
+        };
+        unsafe {
+            llamacpp::sampler_apply(self.chain, &mut view);
+            let logprob = *view.data.offset(view.selected as _);
+            llamacpp::sampler_accept(self.chain, logprob.id);
+            (logprob.id, logprob.p.ln())
+        }
+    }
+}
+
+impl Drop for LlamacppSampler {
+    fn drop(&mut self) {
+        if !self.chain.is_null() {
+            unsafe { llamacpp::sampler_free(self.chain) };
+        }
+    }
+}
+
+struct LlamacppSeq {
+    id: usize,
+    batch_pos: usize,
+    token: llamacpp::llama_token,
+    pos: llamacpp::llama_pos,
+    sampler: LlamacppSampler,
+    text: String,
+    n_new_tokens: usize,
+    running: bool,
+}
+
+static INIT: Once = Once::new();
+
+impl LlamacppBackend {
+    pub fn new(
+        conf: LlamacppConfig,
+        tokenizer: Tokenizer,
+    ) -> (
+        Self,
+        oneshot::Receiver<Result<(), BackendError>>,
+        watch::Sender<bool>,
+    ) {
+        // Setup llama & export logs, once and for all
+        INIT.call_once(|| unsafe {
+            llamacpp::log_set(Some(llamacpp_log_callback), std::ptr::null_mut());
+            llamacpp::backend_init();
+            llamacpp::numa_init(match conf.numa {
+                LlamacppNuma::Disabled => llamacpp::GGML_NUMA_STRATEGY_DISABLED,
+                LlamacppNuma::Distribute => llamacpp::GGML_NUMA_STRATEGY_DISTRIBUTE,
+                LlamacppNuma::Isolate => llamacpp::GGML_NUMA_STRATEGY_ISOLATE,
+                LlamacppNuma::Numactl => llamacpp::GGML_NUMA_STRATEGY_NUMACTL,
+                LlamacppNuma::Mirror => llamacpp::GGML_NUMA_STRATEGY_MIRROR,
+            });
+        });
+
+        let (status_tx, status_rx) = watch::channel(false);
+        let (shutdown_tx, shutdown_rx) = watch::channel(false);
+        let (ok_tx, ok_rx) = oneshot::channel();
+        let (tx, mut rx) = unbounded_channel::<LlamacppRequest>();
+        let (sync_tx, sync_rx) = mpsc::channel();
+
+        spawn(async move {
+            let mut n_tokens = 0;
+            let mut requests = Vec::with_capacity(conf.max_batch_size);
+
+            let flush = |requests: &mut Vec<_>, n_tokens: &mut usize| {
+                if !requests.is_empty() {
+                    let _ =
+                        sync_tx.send(replace(requests, Vec::with_capacity(conf.max_batch_size)));
+                    *n_tokens = 0;
+                }
+            };
+            loop {
+                match timeout(conf.batch_timeout, rx.recv()).await {
+                    Ok(Some(request)) => {
+                        let n_tokens_to_add = request.input_ids.len();
+
+                        if n_tokens + n_tokens_to_add > conf.max_batch_total_tokens {
+                            flush(&mut requests, &mut n_tokens);
+                        }
+                        n_tokens += n_tokens_to_add;
+                        requests.push(request);
+
+                        if requests.len() == conf.max_batch_size {
+                            flush(&mut requests, &mut n_tokens);
+                        }
+                    }
+                    Ok(None) => break,                             // closed
+                    Err(_) => flush(&mut requests, &mut n_tokens), // timeout
+                }
+            }
+        });
+
+        spawn_blocking(move || {
+            let mut llamacpp = match Llamacpp::new(conf) {
+                Ok(v) => {
+                    let _ = ok_tx.send(Ok(()));
+                    v
+                }
+                Err(e) => {
+                    let _ = ok_tx.send(Err(e));
+                    return;
+                }
+            };
+            let vocab = tokenizer.get_added_vocabulary();
+
+            // health() returns true
+            let _ = status_tx.send(true);
+
+            while let Ok(requests) = sync_rx.recv() {
+                if *shutdown_rx.borrow() {
+                    break;
+                }
+                let start_time = Instant::now();
+                let mut seqs: Vec<LlamacppSeq> = Vec::with_capacity(requests.len());
+                llamacpp.batch.n_tokens = 0;
+
+                for (seq_id, request) in requests.iter().enumerate() {
+                    debug!("Request: {:?}", request);
+                    // TODO remove this
+                    let sampler = match LlamacppSampler::new(request) {
+                        Some(sampler) => sampler,
+                        _ => {
+                            let _ = request.tx.send(Err(InferError::IncompleteGeneration));
+                            continue;
+                        }
+                    };
+                    let last_pos = request.input_ids.len() - 1;
+
+                    for (pos, &token_id) in request.input_ids.iter().enumerate() {
+                        llamacpp.batch_push(
+                            token_id as llamacpp::llama_token,
+                            pos as llamacpp::llama_pos,
+                            seq_id as llamacpp::llama_seq_id,
+                            pos == last_pos, // check samplers
+                        );
+                    }
+                    seqs.push(LlamacppSeq {
+                        id: seq_id,
+                        batch_pos: llamacpp.batch.n_tokens as usize - 1,
+                        token: llamacpp::LLAMA_TOKEN_NULL,
+                        pos: last_pos as llamacpp::llama_pos + 1,
+                        sampler,
+                        text: String::with_capacity(1024),
+                        n_new_tokens: 0,
+                        running: true,
+                    });
+                }
+                while llamacpp.batch.n_tokens > 0 {
+                    if llamacpp.decode() != 0 {
+                        warn!("llama_decode failed, clearing kv cache");
+                        llamacpp.clear_kv_cache(-1);
+                        for seq in seqs.iter_mut() {
+                            let _ = requests[seq.id]
+                                .tx
+                                .send(Err(InferError::IncompleteGeneration));
+                            seq.running = false;
+                        }
+                        break;
+                    }
+                    for seq in seqs.iter_mut() {
+                        if !seq.running {
+                            continue;
+                        }
+                        let (next, logprob) = seq.sampler.sample(&mut llamacpp, seq.batch_pos);
+                        seq.n_new_tokens += 1;
+                        seq.token = next;
+
+                        let piece = match tokenizer.decode(&[next as u32], false) {
+                            Ok(piece) => piece,
+                            Err(e) => {
+                                error!("Failed to decode token: {e}");
+                                let _ = requests[seq.id]
+                                    .tx
+                                    .send(Err(InferError::IncompleteGeneration));
+                                seq.running = false;
+                                continue;
+                            }
+                        };
+                        let special = vocab.is_special_token(&piece);
+
+                        if !special {
+                            seq.text.push_str(&piece);
+                        }
+                        let token = Token {
+                            id: next as _,
+                            text: piece,
+                            logprob,
+                            special,
+                        };
+                        let finish: Option<FinishReason> = {
+                            if unsafe { llamacpp::vocab_is_eog(llamacpp.vocab, next) } {
+                                Some(FinishReason::EndOfSequenceToken)
+                            } else if seq.n_new_tokens == requests[seq.id].max_new_tokens {
+                                Some(FinishReason::Length)
+                            } else {
+                                None
+                            }
+                        };
+                        if let Some(reason) = finish {
+                            let _ = requests[seq.id].tx.send(Ok(InferStreamResponse::End {
+                                token,
+                                top_tokens: vec![],
+                                generated_text: GeneratedText {
+                                    text: seq.text.clone(),
+                                    generated_tokens: seq.n_new_tokens as _,
+                                    finish_reason: reason,
+                                    seed: Some(requests[seq.id].seed as _),
+                                },
+                                start: start_time,
+                                queued: requests[seq.id].time,
+                            }));
+                            seq.running = false;
+                            continue;
+                        }
+                        let _ = requests[seq.id]
+                            .tx
+                            .send(Ok(InferStreamResponse::Intermediate {
+                                token,
+                                top_tokens: vec![],
+                            }));
+                    }
+                    // generate a new batch
+                    llamacpp.batch.n_tokens = 0;
+
+                    for seq in seqs.iter_mut() {
+                        if seq.running {
+                            seq.batch_pos =
+                                llamacpp.batch_push(seq.token, seq.pos, seq.id as _, true);
+                            seq.pos += 1;
+                        } else {
+                            llamacpp.clear_kv_cache(seq.id as _);
+                        }
+                    }
+                }
+            }
+        });
+        (
+            Self {
+                tx,
+                status: status_rx,
+            },
+            ok_rx,
+            shutdown_tx,
+        )
+    }
+}
+
+#[async_trait]
+impl Backend for LlamacppBackend {
+    #[instrument(skip_all)]
+    fn schedule(
+        &self,
+        request: ValidGenerateRequest,
+    ) -> Result<UnboundedReceiverStream<Result<InferStreamResponse, InferError>>, InferError> {
+        debug!(?request);
+        let (tx, rx) = unbounded_channel::<Result<InferStreamResponse, InferError>>();
+        match LlamacppRequest::new(&request, tx) {
+            Some(v) => match self.tx.send(v) {
+                Err(e) => Err(InferError::GenerationError(e.to_string())),
+                _ => Ok(UnboundedReceiverStream::new(rx)),
+            },
+            _ => Err(InferError::GenerationError("Bad request".to_string())),
+        }
+    }
+
+    async fn health(&self, _: bool) -> bool {
+        *self.status.borrow()
+    }
+
+    fn name(&self) -> &'static str {
+        "llamacpp"
+    }
+}
+
+#[derive(Debug, Error)]
+pub enum BackendError {
+    #[error("CString error: {0}")]
+    CStringError(#[from] std::ffi::NulError),
+    #[error("Llamacpp error: {0}")]
+    Llamacpp(String),
+}
diff --git a/backends/llamacpp/src/main.rs b/backends/llamacpp/src/main.rs
new file mode 100644
index 00000000000..5a07acdcde9
--- /dev/null
+++ b/backends/llamacpp/src/main.rs
@@ -0,0 +1,284 @@
+mod backend;
+
+use backend::{
+    BackendError, LlamacppBackend, LlamacppConfig, LlamacppGGMLType, LlamacppNuma,
+    LlamacppSplitMode,
+};
+use clap::Parser;
+use text_generation_router::{logging, server, usage_stats};
+use thiserror::Error;
+use tokenizers::{FromPretrainedParameters, Tokenizer};
+use tokio::sync::oneshot::error::RecvError;
+use tracing::{error, warn};
+
+/// Backend Configuration
+#[derive(Parser, Debug)]
+#[clap(author, version, about, long_about = None)]
+struct Args {
+    /// Name of the model to load.
+    #[clap(long, env)]
+    model_id: String,
+
+    /// Revision of the model.
+    #[clap(default_value = "main", long, env)]
+    revision: String,
+
+    /// Path to the GGUF model file for inference.
+    #[clap(long, env)]
+    model_gguf: String, // TODO Option() with hf->gguf & quantize
+
+    /// Number of threads to use for generation.
+    #[clap(long, env)]
+    n_threads: Option<usize>,
+
+    /// Number of threads to use for batch processing.
+    #[clap(long, env)]
+    n_threads_batch: Option<usize>,
+
+    /// Number of layers to store in VRAM.
+    #[clap(default_value = "0", long, env)]
+    n_gpu_layers: usize,
+
+    /// Split the model across multiple GPUs.
+    #[clap(default_value = "layer", long, env)]
+    split_mode: LlamacppSplitMode,
+
+    /// Defragment the KV cache if holes/size > threshold.
+    #[clap(default_value = "-1.0", long, env)]
+    defrag_threshold: f32,
+
+    /// Enable NUMA optimizations.
+    #[clap(default_value = "disabled", value_enum, long, env)]
+    numa: LlamacppNuma,
+
+    /// Use memory mapping for the model.
+    #[clap(long, env)]
+    use_mmap: bool,
+
+    /// Use memory locking to prevent swapping.
+    #[clap(long, env)]
+    use_mlock: bool,
+
+    /// Enable offloading of KQV operations to the GPU.
+    #[clap(long, env)]
+    offload_kqv: bool,
+
+    /// Enable flash attention for faster inference. (EXPERIMENTAL)
+    #[clap(long, env)]
+    flash_attention: bool,
+
+    /// Data type used for K cache.
+    #[clap(default_value = "f16", value_enum, long, env)]
+    type_k: LlamacppGGMLType,
+
+    /// Data type used for V cache.
+    #[clap(default_value = "f16", value_enum, long, env)]
+    type_v: LlamacppGGMLType,
+
+    /// Number of tokenizer workers used for payload validation and truncation.
+    #[clap(default_value = "2", long, env)]
+    validation_workers: usize,
+
+    /// Maximum number of concurrent requests.
+    #[clap(long, env)]
+    max_concurrent_requests: Option<usize>,
+
+    /// Maximum number of input tokens per request.
+    #[clap(default_value = "1024", long, env)]
+    max_input_tokens: usize,
+
+    /// Maximum number of total tokens (input + output) per request.
+    #[clap(default_value = "2048", long, env)]
+    max_total_tokens: usize,
+
+    /// Maximum number of tokens in a batch.
+    #[clap(long, env)]
+    max_batch_total_tokens: Option<usize>,
+
+    /// Maximum number of tokens in a physical batch.
+    #[clap(long, env)]
+    max_physical_batch_total_tokens: Option<usize>,
+
+    /// Maximum number of requests per batch.
+    #[clap(long, env)]
+    max_batch_size: Option<usize>,
+
+    /// IP address to listen on.
+    #[clap(default_value = "0.0.0.0", long)]
+    hostname: String,
+
+    /// Port to listen on.
+    #[clap(default_value = "3000", long, short, env)]
+    port: u16,
+
+    /// Enable JSON output format.
+    #[clap(long, env)]
+    json_output: bool,
+
+    /// OTLP endpoint for telemetry data.
+    #[clap(long, env)]
+    otlp_endpoint: Option<String>,
+
+    /// Service name for OTLP telemetry.
+    #[clap(default_value = "text-generation-inference.router", long, env)]
+    otlp_service_name: String,
+
+    /// Allowed origins for CORS.
+    #[clap(long, env)]
+    cors_allow_origin: Option<Vec<String>>,
+
+    /// Path to the tokenizer configuration file.
+    #[clap(long, env)]
+    tokenizer_config_path: Option<String>,
+
+    /// Disable grammar support.
+    #[clap(long, env)]
+    disable_grammar_support: bool,
+
+    /// Maximum number of inputs per request.
+    #[clap(default_value = "4", long, env)]
+    max_client_batch_size: usize,
+
+    /// Level of usage statistics collection.
+    #[clap(default_value = "on", long, env)]
+    usage_stats: usage_stats::UsageStatsLevel,
+
+    /// Maximum payload size in bytes.
+    #[clap(default_value = "2000000", long, env)]
+    payload_limit: usize,
+}
+
+#[tokio::main]
+async fn main() -> Result<(), RouterError> {
+    let args = Args::parse();
+
+    logging::init_logging(args.otlp_endpoint, args.otlp_service_name, args.json_output);
+
+    let n_threads = match args.n_threads {
+        Some(0) | None => num_cpus::get(),
+        Some(threads) => threads,
+    };
+    let n_threads_batch = match args.n_threads_batch {
+        Some(0) | None => n_threads,
+        Some(threads) => threads,
+    };
+    let max_batch_size = match args.max_batch_size {
+        Some(0) | None => n_threads_batch,
+        Some(threads) => threads,
+    };
+    let max_batch_total_tokens = match args.max_batch_total_tokens {
+        None => max_batch_size * args.max_total_tokens,
+        Some(size) => size,
+    };
+    let max_physical_batch_total_tokens = match args.max_physical_batch_total_tokens {
+        None => max_batch_total_tokens,
+        Some(size) => size,
+    };
+    let max_concurrent_requests = match args.max_concurrent_requests {
+        None => max_batch_size * 2,
+        Some(size) => size,
+    };
+    if args.max_input_tokens >= args.max_total_tokens {
+        return Err(RouterError::ArgumentValidation(
+            "`max_input_tokens` must be < `max_total_tokens`".to_string(),
+        ));
+    }
+    if args.max_total_tokens > max_batch_total_tokens {
+        return Err(RouterError::ArgumentValidation(
+            "`max_total_tokens` must be <= `max_batch_total_tokens`".to_string(),
+        ));
+    }
+    if max_batch_size * args.max_total_tokens > max_batch_total_tokens {
+        return Err(RouterError::ArgumentValidation(
+            "`max_batch_size` * `max_total_tokens` must be <= `max_batch_total_tokens`".to_string(),
+        ));
+    }
+
+    // TODO: check if we use the same cache of Server
+    // check if llamacpp is faster
+    let tokenizer = {
+        let token = std::env::var("HF_TOKEN")
+            .or_else(|_| std::env::var("HUGGING_FACE_HUB_TOKEN"))
+            .ok();
+        let params = FromPretrainedParameters {
+            revision: args.revision.clone(),
+            token,
+            ..Default::default()
+        };
+        Tokenizer::from_pretrained(args.model_id.clone(), Some(params))?
+    };
+
+    let (backend, ok, shutdown) = LlamacppBackend::new(
+        LlamacppConfig {
+            model_gguf: args.model_gguf,
+            n_threads,
+            n_threads_batch,
+            n_gpu_layers: args.n_gpu_layers,
+            split_mode: args.split_mode,
+            defrag_threshold: args.defrag_threshold,
+            numa: args.numa,
+            use_mmap: args.use_mmap,
+            use_mlock: args.use_mlock,
+            flash_attention: args.flash_attention,
+            type_k: args.type_k,
+            type_v: args.type_v,
+            offload_kqv: args.offload_kqv,
+            max_batch_total_tokens,
+            max_physical_batch_total_tokens,
+            max_batch_size,
+            batch_timeout: tokio::time::Duration::from_millis(5),
+        },
+        tokenizer,
+    );
+    ok.await??;
+
+    if cfg!(debug_assertions) {
+        warn!("Graceful shutdown disabled!");
+        let _ = tokio::task::spawn(async move {
+            let _ = tokio::signal::ctrl_c().await;
+            let _ = shutdown.send(true);
+        });
+    }
+
+    server::run(
+        backend,
+        max_concurrent_requests,
+        0, // max_best_of
+        0, // max_stop_sequences
+        0, // max_top_n_tokens
+        args.max_input_tokens,
+        args.max_total_tokens,
+        args.validation_workers,
+        None,          // api_key
+        args.model_id, // tokenizer_name
+        args.tokenizer_config_path,
+        Some(args.revision),
+        false, // trust_remote_code
+        args.hostname,
+        args.port,
+        args.cors_allow_origin,
+        false, // ngrok,
+        None,  // ngrok_authtoken,
+        None,  // ngrok_edge,
+        args.disable_grammar_support,
+        args.max_client_batch_size,
+        args.usage_stats,
+        args.payload_limit,
+    )
+    .await?;
+    Ok(())
+}
+
+#[derive(Debug, Error)]
+enum RouterError {
+    #[error("Argument validation error: {0}")]
+    ArgumentValidation(String),
+    #[error("Tokenizer error: {0}")]
+    Tokenizer(#[from] tokenizers::Error),
+    #[error("Backend error: {0}")]
+    Backend(#[from] BackendError),
+    #[error("WebServer error: {0}")]
+    WebServer(#[from] server::WebServerError),
+    #[error("Recv error: {0}")]
+    RecvError(#[from] RecvError),
+}
diff --git a/docs/source/_toctree.yml b/docs/source/_toctree.yml
index 8fcba516bd2..e073353fca9 100644
--- a/docs/source/_toctree.yml
+++ b/docs/source/_toctree.yml
@@ -52,6 +52,8 @@
 - sections:
   - local: backends/trtllm
     title: TensorRT-LLM
+  - local: backends/llamacpp
+    title: Llamacpp
   title: Backends
 - sections:
   - local: reference/launcher
diff --git a/docs/source/backends/llamacpp.md b/docs/source/backends/llamacpp.md
new file mode 100644
index 00000000000..dbd93e86606
--- /dev/null
+++ b/docs/source/backends/llamacpp.md
@@ -0,0 +1,120 @@
+# Llamacpp Backend
+
+The llamacpp backend facilitates the deployment of large language models
+(LLMs) by integrating [llama.cpp][llama.cpp], an advanced inference engine
+optimized for both CPU and GPU computation. This backend is a component
+of Hugging Face’s **Text Generation Inference (TGI)** suite,
+specifically designed to streamline the deployment of LLMs in production
+environments.
+
+## Key Capabilities
+
+- Full compatibility with GGUF format and all quantization formats
+  (GGUF-related constraints may be mitigated dynamically by on-the-fly
+  generation in future updates)
+- Optimized inference on CPU and GPU architectures
+- Containerized deployment, eliminating dependency complexity
+- Seamless interoperability with the Hugging Face ecosystem
+
+## Model Compatibility
+
+This backend leverages models formatted in **GGUF**, providing an
+optimized balance between computational efficiency and model accuracy.
+You will find the best models on [Hugging Face][GGUF].
+
+## Build Docker image
+
+For optimal performance, the Docker image is compiled with native CPU
+instructions, thus it's highly recommended to execute the container on
+the host used during the build process. Efforts are ongoing to enhance
+portability while maintaining high computational efficiency.
+
+```bash
+docker build \
+    -t tgi-llamacpp \
+    https://github.com/huggingface/text-generation-inference.git \
+    -f Dockerfile_llamacpp
+```
+
+### Build parameters
+
+| Parameter                            | Description                       |
+| ------------------------------------ | --------------------------------- |
+| `--build-arg llamacpp_version=bXXXX` | Specific version of llama.cpp     |
+| `--build-arg llamacpp_cuda=ON`       | Enables CUDA acceleration         |
+| `--build-arg cuda_arch=ARCH`         | Defines target CUDA architecture  |
+
+## Model preparation
+
+Retrieve a GGUF model and store it in a specific directory, for example:
+
+```bash
+mkdir -p ~/models
+cd ~/models
+curl -LOJ "https://huggingface.co/Qwen/Qwen2.5-3B-Instruct-GGUF/resolve/main/qwen2.5-3b-instruct-q4_0.gguf?download=true"
+```
+
+## Run Docker image
+
+### CPU-based inference
+
+```bash
+docker run \
+    -p 3000:3000 \
+    -e "HF_TOKEN=$HF_TOKEN" \
+    -v "$HOME/models:/models" \
+    tgi-llamacpp \
+    --model-id "Qwen/Qwen2.5-3B-Instruct" \
+    --model-gguf "/models/qwen2.5-3b-instruct-q4_0.gguf"
+```
+
+### GPU-Accelerated inference
+
+```bash
+docker run \
+    --gpus all \
+    -p 3000:3000 \
+    -e "HF_TOKEN=$HF_TOKEN" \
+    -v "$HOME/models:/models" \
+    tgi-llamacpp \
+    --n-gpu-layers 99
+    --model-id "Qwen/Qwen2.5-3B-Instruct" \
+    --model-gguf "/models/qwen2.5-3b-instruct-q4_0.gguf"
+```
+
+## Advanced parameters
+
+A full listing of configurable parameters is available in the `--help`:
+
+```bash
+docker run tgi-llamacpp --help
+
+```
+
+The table below summarizes key options:
+
+| Parameter                           | Description                                                            |
+|-------------------------------------|------------------------------------------------------------------------|
+| `--n-threads`                       | Number of threads to use for generation                                |
+| `--n-threads-batch`                 | Number of threads to use for batch processing                          |
+| `--n-gpu-layers`                    | Number of layers to store in VRAM                                      |
+| `--split-mode`                      | Split the model across multiple GPUs                                   |
+| `--defrag-threshold`                | Defragment the KV cache if holes/size > threshold                      |
+| `--numa`                            | Enable NUMA optimizations                                              |
+| `--use-mmap`                        | Use memory mapping for the model                                       |
+| `--use-mlock`                       | Use memory locking to prevent swapping                                 |
+| `--offload-kqv`                     | Enable offloading of KQV operations to the GPU                         |
+| `--flash-attention`                 | Enable flash attention for faster inference                            |
+| `--type-k`                          | Data type used for K cache                                             |
+| `--type-v`                          | Data type used for V cache                                             |
+| `--validation-workers`              | Number of tokenizer workers used for payload validation and truncation |
+| `--max-concurrent-requests`         | Maximum number of concurrent requests                                  |
+| `--max-input-tokens`                | Maximum number of input tokens per request                             |
+| `--max-total-tokens`                | Maximum number of total tokens (input + output) per request            |
+| `--max-batch-total-tokens`          | Maximum number of tokens in a batch                                    |
+| `--max-physical-batch-total-tokens` | Maximum number of tokens in a physical batch                           |
+| `--max-batch-size`                  | Maximum number of requests per batch                                   |
+
+---
+[llama.cpp]: https://github.com/ggerganov/llama.cpp
+[GGUF]: https://huggingface.co/models?library=gguf&sort=trending
diff --git a/docs/source/multi_backend_support.md b/docs/source/multi_backend_support.md
index c4df15bc2ca..03d6d30be55 100644
--- a/docs/source/multi_backend_support.md
+++ b/docs/source/multi_backend_support.md
@@ -11,3 +11,5 @@ TGI remains consistent across backends, allowing you to switch between them seam
 * **[TGI TRTLLM backend](./backends/trtllm)**: This backend leverages NVIDIA's TensorRT library to accelerate LLM inference.
   It utilizes specialized optimizations and custom kernels for enhanced performance.
   However, it requires a model-specific compilation step for each GPU architecture.
+* **[TGI Llamacpp backend](./backends/llamacpp)**: This backend facilitates the deployment of large language models
+  (LLMs) by integrating [llama.cpp][llama.cpp], an advanced inference engine optimized for both CPU and GPU computation.