Conversation
Summary of ChangesHello @zhyncs, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request focuses on a routine maintenance task: updating the version of the Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
There was a problem hiding this comment.
Code Review
This pull request bumps the version of sgl-kernel to 0.3.11 across several project files. The changes are mostly straightforward version updates. However, I've noticed that docker/Dockerfile and a GitHub workflow file have been removed from the automatic version update script in the Makefile. This could lead to version inconsistencies in the future, as the Docker build might use an outdated kernel version. I've left a comment with more details.
| pyproject_cpu.toml \ | ||
| ../docker/Dockerfile \ | ||
| ../.github/workflows/pr-test-pd-router.yml | ||
| pyproject_cpu.toml |
There was a problem hiding this comment.
Removing ../docker/Dockerfile and ../.github/workflows/pr-test-pd-router.yml from FILES_TO_UPDATE will prevent the make update command from updating version numbers in these files. This can lead to inconsistencies and outdated builds. For instance, docker/Dockerfile on line 88 still references version 0.3.10. This will cause Docker images to be built with an outdated kernel. Was this change intentional? If not, I recommend re-adding those files to FILES_TO_UPDATE to ensure consistent versioning across the project.
pyproject_cpu.toml \
../docker/Dockerfile \
../.github/workflows/pr-test-pd-router.yml
* origin/qwen3: (30 commits) chore: bump sgl-kernel 0.3.11 (sgl-project#10630) feat: add fused moe config for Qwen3-Next-80B-A3B-Instruct on B200 (sgl-project#10631) model support: Sarashina2VisionForCausalLM (sgl-project#10632) [Performance] Qwen3-Next: speed up update_mamba_state_after_mtp_verify by 10x; e2e up to 3.54% faster (sgl-project#10586) [Performance] Qwen3-Next: replace arange to cached query_start_loc_li… (sgl-project#10553) [Feature] Speculative decoding support lookahead (sgl-project#9873) refactor: use registry for _get_attention_backend_from_str (sgl-project#10629) [router] refactor worker to builder pattern 1/n (sgl-project#10628) Garbage collector regression in the online server (sgl-project#10621) feat: Add FlexAttention Backend for Efficient Sparse Attention (sgl-project#9947) Fix bias handling in TritonMoeQuantInfo within quantization/mxfp4.py (sgl-project#10579) [Performance] qwen3-next improve causal conv1d in prefill phase (sgl-project#10595) Fix sgl_kernel import failure on devices other than CUDA (sgl-project#10610) support qwen3-next-fp8 deepep (sgl-project#10622) update deepep version for qwen3-next deepep moe (sgl-project#10624) Feat/add heartbeat mechanism for nixl conn (sgl-project#10222) [RL] Add destroy process group api (sgl-project#9979) fix deepep assert when PD disaggregation == null (sgl-project#8274) Scale kkt after reduction (sgl-project#10604) [improvement] add average input/output token length for hicache benchmark stats output (sgl-project#10525) ...
Motivation
Modifications
Accuracy Tests
Benchmarking and Profiling
Checklist