Bump TensorRT-LLM backend dependency to v0.16.0 (#2931)

* backend(trtllm): update to 0.16.0

* backend(trtllm): do not use shallow clone

* backend(trtllm): use tag instead

* backend(trtllm): move to nvidia remote instead of hf

* backend(trtllm): reenable shallow clone

* backend(trtllm): attempt to use ADD instead of RUN for openmpi

* backend(trtllm): make sure we are using correct path for openmpi ADD in dockerfile

* backend(trtllm): add correctly untar it

Author: mfuntowicz

Dockerfile_trtllm

@@ -1,5 +1,5 @@
 ARG cuda_arch_list="75-real;80-real;86-real;89-real;90-real"
-ARG ompi_version="4.1.7rc1"
+ARG ompi_version="4.1.7"
 ARG build_type=release
 ARG is_gha_build=false
 
@@ -37,10 +37,12 @@ FROM cuda-builder AS mpi-builder
 ARG ompi_version
 
 ENV OMPI_TARBALL_FILENAME="openmpi-$ompi_version.tar.bz2"
-RUN wget "https://download.open-mpi.org/release/open-mpi/v4.1/$OMPI_TARBALL_FILENAME" -P /opt/src && \
-    mkdir /usr/src/mpi && \
-    tar -xf "/opt/src/$OMPI_TARBALL_FILENAME" -C /usr/src/mpi --strip-components=1 && \
-    cd /usr/src/mpi && \
+ADD --checksum=sha256:54a33cb7ad81ff0976f15a6cc8003c3922f0f3d8ceed14e1813ef3603f22cd34 \
+    https://download.open-mpi.org/release/open-mpi/v4.1/$OMPI_TARBALL_FILENAME \
+    /opt/src/mpi/
+
+WORKDIR /opt/src/mpi
+RUN tar --strip-components=1 -xf $OMPI_TARBALL_FILENAME &&\
     ./configure --prefix=/usr/local/mpi --with-cuda=/usr/local/cuda --with-slurm && \
     make -j all && \
     make install && \

backends/trtllm/cmake/trtllm.cmake

@@ -27,8 +27,8 @@ find_package(Python3 REQUIRED Interpreter)
 
 fetchcontent_declare(
         trtllm
-        GIT_REPOSITORY https://github.com/huggingface/TensorRT-LLM.git
-        GIT_TAG 1bb9ca4688805444f203647674bac1d7219d0579
+        GIT_REPOSITORY https://github.com/nvidia/TensorRT-LLM.git
+        GIT_TAG v0.16.0
         GIT_SHALLOW ON
         DOWNLOAD_EXTRACT_TIMESTAMP
 )

backends/trtllm/scripts/install_tensorrt.sh

@@ -2,8 +2,8 @@
 
 set -ex
 
-TRT_VER_BASE="10.6.0"
-TRT_VER_FULL="${TRT_VER_BASE}.26"
+TRT_VER_BASE="10.7.0"
+TRT_VER_FULL="${TRT_VER_BASE}.23"
 CUDA_VER="12.6"
 CUDNN_VER="9.5.0.50-1"
 NCCL_VER="2.22.3-1+cuda12.6"