sglang
https://github.com/sgl-project/sglang
Python
SGLang is a high-performance serving framework for large language models and multimodal models.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to sglang
Help out
- Issues
- [router] Break the SSE pump on client disconnect even while the upstream is pending
- [Bug] [MLX] SchedulerProfilerManager._start_profile returns success=False under mocked Metal capture
- [Bug] RuntimeError in DSA attention backend during EAGLE verify when sequence approaches `context-length` (tensor size mismatch 614406 vs 614408)
- SGLang not support hidden_size=4096, moe_intermediate_size=2048 MoE
- [SUPA][1/N] Add device detection and check_env support
- fix: write_through_selective double-counts hits from same request lif…
- ci: self-heal missing nvidia CUDA libs (fix torch-import wedge on runners)
- [Bugfix] Support gated ModelOpt NVFP4 MoE intermediate padding
- [Fix] Check paged allocator capacity before kernel launch
- [Refactor] Unify HiSparse device-pool mapping internals
- Docs
- Python not yet supported