Support vLLM 0.28 (issue #84) - #132
Draft
yairallouche wants to merge 1 commit into
Draft
yairallouche wants to merge 1 commit into
yairallouche wants to merge 1 commit into
Conversation
Migrate the second, mutually-exclusive vLLM line from 0.20 to 0.28, keeping the 0.19.1 default track unchanged. vLLM 0.28 hard-pins torch==2.13.0 (with torchvision 0.28 / triton 3.7.1), pulled in per dependency-group so the two tracks never share a lockfile resolution. - pyproject.toml: vllm20 extra/group -> vllm28 (>=0.28.0,<0.29.0); dev-vllm20 -> dev-vllm28; all [tool.uv].conflicts entries updated. Raise transformers cap to <5.16.0 (vLLM 0.28 requires only >=5.5.3; uv resolves a single 5.8.x shared across both tracks). - .github/workflows/gpu-tests.yaml: matrix leg vllm20/dev-vllm20 -> vllm28/dev-vllm28; refresh stale comments. - uv.lock: regenerated; resolves vllm 0.19.1 + 0.28.0, torch 2.10 + 2.13, triton 3.6 + 3.7.1, torchvision 0.25 + 0.28. - Docs/comments swept vllm20 -> vllm28 (README, AUDIO, PREREQUISITES, audio test docstring fact). Co-Authored-By: Claude Opus 4.8 <[email protected]>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Migrates the second, mutually-exclusive vLLM track from 0.20 to 0.28, keeping the 0.19.1 default track unchanged. Tracks issue generative-computing/granite-switch-staging#84.
Changes
vllm20extra/group →vllm28(>=0.28.0,<0.29.0);dev-vllm20→dev-vllm28; all[tool.uv].conflictsupdated. transformers cap raised to<5.16.0(vLLM 0.28 requires only>=5.5.3).vllm20/dev-vllm20→vllm28/dev-vllm28.vllm20→vllm28.vLLM 0.28 hard-pins torch==2.13.0 (torchvision 0.28 / triton 3.7.1), pulled per dependency-group so the two tracks never share a lockfile resolution.
Status
Draft while the GPU test suite runs against the 0.28 leg. Will iterate on any failures the run surfaces.
🤖 Generated with Claude Code