Skip to content

Bump vllm 0.21.0#261

Open
mgsalem wants to merge 4 commits into
mainfrom
bump-vllm-0.21.0
Open

Bump vllm 0.21.0#261
mgsalem wants to merge 4 commits into
mainfrom
bump-vllm-0.21.0

Conversation

@mgsalem
Copy link
Copy Markdown
Collaborator

@mgsalem mgsalem commented May 20, 2026

PR Type

Other (dependency bump)

Short Description

Bumps the vllm backend from 0.19.0 to 0.21.0. Regenerated uv.lock with
uv lock --upgrade-package vllm, which also pulled the transitive updates
0.21.0 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

mgsalem added 4 commits May 20, 2026 18:20
…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.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant