huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

misc(backend): let's try

Browse Source
This commit is contained in:
Morgan Funtowicz 2024-12-20 11:56:02 +01:00
parent ebb3e51882
commit 8609f0d46f
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.github/workflows/build_trtllm.yaml vendored
View File

@ -32,7 +32,7 @@ jobs:
- name: Extract TensorRT-LLM version - name: Extract TensorRT-LLM version
run: | run: |
echo "TENSORRT_LLM_VERSION=$(grep -oP '([a-z,0-9]{40})' backends/trtllm/cmake/trtllm.cmake)" >> $GITHUB_ENV echo "TENSORRT_LLM_VERSION=$(grep -oP '([a-z,0-9]{40})' $GITHUB_WORKSPACE/text-generation-inference/backends/trtllm/cmake/trtllm.cmake)" >> $GITHUB_ENV
echo "TensorRT-LLM version: $TENSORRT_LLM_VERSION" echo "TensorRT-LLM version: $TENSORRT_LLM_VERSION"
- name: "Configure AWS Credentials" - name: "Configure AWS Credentials"
@ -115,8 +115,8 @@ jobs:
sccache_bucket=${{ secrets.AWS_S3_BUCKET_GITHUB_TGI_TEST }} sccache_bucket=${{ secrets.AWS_S3_BUCKET_GITHUB_TGI_TEST }}
sccache_s3_key_prefix=trtllm-${{ env.TENSORRT_LLM_VERSION }} sccache_s3_key_prefix=trtllm-${{ env.TENSORRT_LLM_VERSION }}
sccache_region=us-east-1 sccache_region=us-east-1
cache-from: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache-${{ env.LABEL }}-trtllm,mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min cache-from: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache-${{ env.LABEL }},mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
cache-to: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache-${{ env.LABEL }}-trtllm,mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min cache-to: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache-${{ env.LABEL }},mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min

2
Dockerfile_trtllm
View File

@ -104,7 +104,7 @@ COPY backends/trtllm backends/trtllm
COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi
RUN mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$TGI_INSTALL_PREFIX/lib" && \ RUN mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$TGI_INSTALL_PREFIX/lib" && \
# python3 scripts/setup_sccache.py --is-gha-build ${is_gha_build} -k ${aws_access_key_id} -s ${aws_secret_key_id} -t ${aws_session_token} -b ${sccache_bucket} -r ${sscache_region} -p ${sccache_s3_key_prefix } && \ python3 scripts/setup_sccache.py --is-gha-build ${is_gha_build} -k ${aws_access_key_id} -s ${aws_secret_key_id} -t ${aws_session_token} -b ${sccache_bucket} -r ${sscache_region} -p ${sccache_s3_key_prefix } && \
RUSTC_WRAPPER=sccache CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --profile ${build_type} --package text-generation-backends-trtllm --bin text-generation-backends-trtllm RUSTC_WRAPPER=sccache CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --profile ${build_type} --package text-generation-backends-trtllm --bin text-generation-backends-trtllm
FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 AS runtime FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 AS runtime