feat: add Containerfile for building vllm CPU images #4
nathan-weinbergAnnotations
1 error and 1 warning
|
build-test-push (linux/amd64)
buildx failed with: ERROR: failed to build: failed to solve: process "/bin/sh -c if [ -z \"${INFERENCE_MODEL}\" ]; then echo \"ERROR: INFERENCE_MODEL build argument is required\" >&2 && exit 1; fi && if [ -z \"${EMBEDDING_MODEL}\" ]; then echo \"ERROR: EMBEDDING_MODEL build argument is required\" >&2 && exit 1; fi" did not complete successfully: exit code: 1
|
|
build-test-push (linux/amd64)
No file matched to [/home/runner/work/llama-stack-distribution/llama-stack-distribution/**/*requirements*.txt,/home/runner/work/llama-stack-distribution/llama-stack-distribution/**/*requirements*.in,/home/runner/work/llama-stack-distribution/llama-stack-distribution/**/*constraints*.txt,/home/runner/work/llama-stack-distribution/llama-stack-distribution/**/*constraints*.in,/home/runner/work/llama-stack-distribution/llama-stack-distribution/**/pyproject.toml,/home/runner/work/llama-stack-distribution/llama-stack-distribution/**/uv.lock,/home/runner/work/llama-stack-distribution/llama-stack-distribution/**/*.py.lock]. The cache will never get invalidated. Make sure you have checked out the target repository and configured the cache-dependency-glob input correctly.
|
Artifacts
Produced during runtime
| Name | Size | Digest | |
|---|---|---|---|
|
opendatahub-io~llama-stack-distribution~G0SD95.dockerbuild
|
32.4 KB |
sha256:8fe9479f2f45d4d97db5d4c75023b73df1f8241af0553426a6f8fa9a974db915
|
|