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
- [ROCm] Add Triton sparse-MLA prefill and decode for gfx950
- Fix HYV4 silently computing one token in attn_tp_size with an a2a MoE backend
- Add the expert-location hook to HYV4ForCausalLM
- Do not require expert-location metadata when no EPLB dispatch algorithm is set
- [Fix] Explain disabled DP attention in TBO validation
- Make int8 mamba checkpoint pool compatible with Qwen4-Exp PLE side states
- [Bug] qwen3_coder: stop harvesting phantom tool_calls from quoted markup
- fix: interior grid-boundary mamba ch
- [Scheduler] Disable chunked prefill for encoder-decoder models
- [Bug] Chunked prefill splits the encoder region of encoder-decoder models, corrupting `extend_num_tokens` and crashing the scheduler
- Docs
- Python not yet supported