mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-11 04:14:52 +00:00
...
This commit is contained in:
parent
0cd364f313
commit
d743252d44
@ -209,14 +209,15 @@ ENV UV_SYSTEM_PYTHON=1
|
|||||||
ENV HF_KERNELS_CACHE=/kernels
|
ENV HF_KERNELS_CACHE=/kernels
|
||||||
RUN cd server && \
|
RUN cd server && \
|
||||||
pip install -U pip uv && \
|
pip install -U pip uv && \
|
||||||
uv sync --frozen --extra gen --extra attention --extra bnb --extra accelerate --extra compressed-tensors --extra marlin --extra moe --extra quantize --extra peft --extra outlines --extra nvidia-nccl-cu12 --no-install-project && \
|
uv sync --frozen --extra gen --extra attention --extra bnb --extra accelerate --extra compressed-tensors --extra marlin --extra moe --extra quantize --extra peft --extra outlines --no-install-project && \
|
||||||
. ./.venv/bin/activate && \
|
. ./.venv/bin/activate && \
|
||||||
make gen-server-raw && \
|
make gen-server-raw && \
|
||||||
hf-kernels download .
|
hf-kernels download .
|
||||||
|
|
||||||
RUN cd server && \
|
RUN cd server && \
|
||||||
uv sync --frozen --extra gen --extra attention --extra bnb --extra accelerate --extra compressed-tensors --extra marlin --extra moe --extra quantize --extra peft --extra outlines --extra nvidia-nccl-cu12 && \
|
uv sync --frozen --extra gen --extra attention --extra bnb --extra accelerate --extra compressed-tensors --extra marlin --extra moe --extra quantize --extra peft --extra outlines && \
|
||||||
. ./.venv/bin/activate && \
|
. ./.venv/bin/activate && \
|
||||||
|
uv pip install nvidia-nccl-cu12==2.22.3 && \
|
||||||
pwd && \
|
pwd && \
|
||||||
text-generation-server --help
|
text-generation-server --help
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user