huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-09 03:14:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixing the makefile by using lockfile.

Browse Source
This commit is contained in:
Nicolas Patry 2025-04-24 15:30:51 +02:00
parent 90989a4a04
commit d7a609d4ad
No known key found for this signature in database
GPG Key ID: 87B37D879D09DEB4
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
server/Makefile
View File

@ -10,6 +10,7 @@ include Makefile-flashinfer
unit-tests:
pip install -U pip uv
uv pip install -e ".[dev]"
uv sync --inexact --extra dev --active
pytest -s -vv -m "not private" tests
gen-server:
@ -30,14 +31,14 @@ gen-server-raw:
touch text_generation_server/pb/__init__.py
install-server: gen-server
uv pip install -e ".[accelerate, compressed-tensors, quantize, peft, outlines]"
uv sync --inexact --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines --active
install: install-cuda
echo "Installed server"
install-cuda: install-server install-flash-attention-v2-cuda install-flash-attention
uv pip install -e ".[attention,bnb,marlin,moe]"
uv sync --inexact --extra attention --extra bnb --extra marlin --extra moe --active
uv pip install nvidia-nccl-cu12==2.22.3
kernels download .