Skip to content

Commit

Permalink
Add compressed-tensors dependency
Browse files Browse the repository at this point in the history
  • Loading branch information
danieldk committed Nov 8, 2024
1 parent c431c5d commit 8311452
Show file tree
Hide file tree
Showing 3 changed files with 25 additions and 3 deletions.
2 changes: 1 addition & 1 deletion server/Makefile
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ gen-server:
install-server: gen-server
pip install pip --upgrade
pip install -r requirements_cuda.txt
pip install -e ".[accelerate, quantize, peft, outlines]"
pip install -e ".[accelerate, compressed-tensors, quantize, peft, outlines]"


install: install-cuda
Expand Down
24 changes: 22 additions & 2 deletions server/poetry.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 2 additions & 0 deletions server/pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@ pillow = "^10.0.0"
outlines= { version = "^0.0.34", optional = true }
prometheus-client = "^0.20.0"
py-cpuinfo = "^9.0.0"
compressed-tensors = { version = "^0.7.1", optional = true }
# Remove later, temporary workaround for outlines.
numpy = "^1.26"

Expand All @@ -58,6 +59,7 @@ rich = "^13.7.1"
torch = ["torch"]
accelerate = ["accelerate"]
bnb = ["bitsandbytes"]
compressed-tensors = ["compressed-tensors"]
marlin = ["marlin-kernels"]
moe = ["moe-kernels"]
peft = ["peft"]
Expand Down

0 comments on commit 8311452

Please sign in to comment.