mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-10 20:04:52 +00:00
Fix dockerfile.
This commit is contained in:
parent
97292ec21c
commit
e27438aac0
@ -121,7 +121,7 @@ FROM kernel-builder as awq-kernels-builder
|
|||||||
WORKDIR /usr/src
|
WORKDIR /usr/src
|
||||||
COPY server/Makefile-awq Makefile
|
COPY server/Makefile-awq Makefile
|
||||||
# Build specific version of transformers
|
# Build specific version of transformers
|
||||||
RUN TORCH_CUDA_ARCH_LIST="8.0;8.6" make build-awq
|
RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" make build-awq
|
||||||
|
|
||||||
# Build Transformers CUDA kernels
|
# Build Transformers CUDA kernels
|
||||||
FROM kernel-builder as custom-kernels-builder
|
FROM kernel-builder as custom-kernels-builder
|
||||||
@ -175,8 +175,8 @@ COPY --from=flash-att-v2-builder /usr/src/flash-attention-v2/build/lib.linux-x86
|
|||||||
COPY --from=custom-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
|
COPY --from=custom-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
|
||||||
# Copy build artifacts from exllama kernels builder
|
# Copy build artifacts from exllama kernels builder
|
||||||
COPY --from=exllama-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
|
COPY --from=exllama-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
|
||||||
# Copy build artifacts from exllama kernels builder
|
# Copy build artifacts from awq kernels builder
|
||||||
COPY --from=awq-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
|
COPY --from=awq-kernels-builder /usr/src/llm-awq/awq/kernels/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
|
||||||
|
|
||||||
# Copy builds artifacts from vllm builder
|
# Copy builds artifacts from vllm builder
|
||||||
COPY --from=vllm-builder /usr/src/vllm/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
|
COPY --from=vllm-builder /usr/src/vllm/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
|
||||||
|
@ -1,6 +1,7 @@
|
|||||||
awq_commit := f084f40bd996f3cf3a0633c1ad7d9d476c318aaa
|
awq_commit := f084f40bd996f3cf3a0633c1ad7d9d476c318aaa
|
||||||
|
|
||||||
awq:
|
awq:
|
||||||
|
rm -rf llm-awq
|
||||||
git clone https://github.com/mit-han-lab/llm-awq
|
git clone https://github.com/mit-han-lab/llm-awq
|
||||||
|
|
||||||
build-awq: awq
|
build-awq: awq
|
||||||
|
Loading…
Reference in New Issue
Block a user