Skip to content

GitLab

Unverified Commit d3b0cae1 authored by Kyle McGill's avatar Kyle McGill Committed by GitHub
Browse files

chore: vLLM arm build has verbose logging turned on to see progress (#1160)

parent 3d697d4d
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
container/Dockerfile.vllm
View file @ d3b0cae1
...@@ -192,7 +192,7 @@ RUN --mount=type=bind,source=./container/deps/,target=/tmp/deps \ ...@@ -192,7 +192,7 @@ RUN --mount=type=bind,source=./container/deps/,target=/tmp/deps \
# MAX_JOBS set to avoid running OOM on vllm-flash-attn build, this can # MAX_JOBS set to avoid running OOM on vllm-flash-attn build, this can
# significantly impact the overall build time. Each job can take up # significantly impact the overall build time. Each job can take up
# to -16GB RAM each, so tune according to available system memory. # to -16GB RAM each, so tune according to available system memory.
MAX_JOBS=${VLLM_MAX_JOBS} uv pip install . --no-build-isolation ; \ MAX_JOBS=${VLLM_MAX_JOBS} uv pip install -vv . --no-build-isolation ; \
# Handle x86_64: Download wheel, unpack, setup for later steps # Handle x86_64: Download wheel, unpack, setup for later steps
else \ else \
python -m pip download --only-binary=:all: --no-deps --dest /tmp/vllm vllm==v${VLLM_REF} && \ python -m pip download --only-binary=:all: --no-deps --dest /tmp/vllm vllm==v${VLLM_REF} && \
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment