python312Packages.vllm: 0.9.0.1 -> 0.9.1#416385
Merged
happysalada merged 3 commits intoNixOS:masterfrom Jun 18, 2025
Merged
Conversation
Contributor
Author
|
Seems to be broken on CPU as doesn't appear to properly handle the optional Still need to test with CUDA. |
09f1f90 to
ae41f83
Compare
fa78820 to
778c9c1
Compare
Contributor
Author
|
I was mistaken about being newly broken on CPU - it fails with some configuration options, but seems this was not changed since the last release. Seems to be working OK. Also tested working on CUDA. |
Contributor
Author
6c703c9 to
2a25eed
Compare
Contributor
|
Contributor
Author
|
Should probably disable for python313: vllm-project/vllm#12083 |
2a25eed to
e58aa1c
Compare
13 tasks
13 tasks
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Things done
Update python312Packages.vllm to v0.9.1
python312Packages.xgrammar: 0.1.14 -> 0.1.19
python312Packages.py-libnuma: init at 1.2
The substituteInPlace call previously used to disable
ncclon unsupported platforms broke, and has been replaced with a patch.Added
torch.stdenv.ccto vllmdependencies, as it expects CC to be available for dynamo recompilation at runtime.nix.conf? (See Nix manual)sandbox = relaxedsandbox = truenix-shell -p nixpkgs-review --run "nixpkgs-review rev HEAD". Note: all changes have to be committed, also see nixpkgs-review usage./result/bin/)Add a 👍 reaction to pull requests you find important.