mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-13 22:18:36 +08:00
[None][fix] Remove the wheel from intermediate docker storage (#7175)
Signed-off-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
This commit is contained in:
parent
9d345b31c0
commit
7cfa475e05
@ -131,11 +131,8 @@ FROM ${DEVEL_IMAGE} AS release
|
||||
RUN mkdir -p /root/.cache/pip
|
||||
|
||||
WORKDIR /app/tensorrt_llm
|
||||
COPY --from=wheel /src/tensorrt_llm/build/tensorrt_llm*.whl .
|
||||
RUN --mount=type=cache,target=/root/.cache/pip \
|
||||
pip install tensorrt_llm*.whl && \
|
||||
rm tensorrt_llm*.whl && \
|
||||
pip cache purge
|
||||
RUN --mount=type=cache,target=/root/.cache/pip --mount=type=bind,from=wheel,source=/src/tensorrt_llm/build,target=/tmp/wheel \
|
||||
pip install /tmp/wheel/tensorrt_llm*.whl
|
||||
|
||||
COPY README.md ./
|
||||
COPY docs docs
|
||||
|
||||
@ -11,6 +11,7 @@
|
||||
#
|
||||
# NB: Typically, the suffix indicates the PR whose CI pipeline generated the images. In case that
|
||||
# images are adopted from PostMerge pipelines, the abbreviated commit hash is used instead.
|
||||
IMAGE_NAME=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm
|
||||
LLM_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.06-py3-x86_64-ubuntu24.04-trt10.11.0.33-skip-tritondevel-202508201630-pre-test
|
||||
LLM_SBSA_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.06-py3-aarch64-ubuntu24.04-trt10.11.0.33-skip-tritondevel-202508201630-pre-test
|
||||
LLM_ROCKYLINUX8_PY310_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-12.9.1-devel-rocky8-x86_64-rocky8-py310-trt10.11.0.33-skip-tritondevel-202508201630-pre-test
|
||||
|
||||
Loading…
Reference in New Issue
Block a user