Bump vllm 0.21.0#261
Merged
Merged
Conversation
…ock at build time - docker.yml: auth via WIF, push to GAR. Registry coordinates come from GCP_AR_REGION/GCP_PROJECT_ID/GCP_AR_REPOSITORY variables and GCP_WIF_PROVIDER/GCP_WIF_SERVICE_ACCOUNT secrets. - vllm.Dockerfile, sglang.Dockerfile: install pinned to uv.lock via 'uv export --frozen | uv pip install --no-deps' (uv pip install alone ignores the lockfile). Adds a build-time import canary. - README and docs/index: point to GAR.
Resolve uv.lock conflict: keep the 0.21.0 resolution's sglang-only markers for nvidia-*-cu12 libs (vllm 0.21.0/torch 2.11 moved to CUDA 13 wheels, so the cu12 packages are now sglang-only). lxml 6.1.0 bump from main preserved via clean auto-merge.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR Type
Other (dependency bump)
Short Description
Bumps the vllm backend from 0.19.0 to 0.21.0. Regenerated
uv.lockwithuv lock --upgrade-package vllm, which also pulled the transitive updates0.21.0 requires (torch 2.10→2.11, torchaudio/torchvision/xgrammar, added
z3-solver/tilelang/nvidia-* libs, removed resampy).
Tests Added
None — dependency-only change. Validated by the docker workflow's build-time