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
- Add FlashInfer prefill context parallelism
- [Bug] MiniMax-H3 occurs args error
- [diffusion] vae: fix silently ignored --vae-tiling for Sana (AutoencoderDC)
- Fix graceful shutdown: drain survives group-delivered stop signals
- [Kimi K3] Exclude template-rendered response_format tokens from billed prompt_tokens
- feat(npu): llguidance bitmask path for Ascend NPU (#1107)
- [Bug] DFLASH speculative decoding is not supported under PD disaggregation: spec_info None crash, then watchdog self-kill
- [Mamba] Thin cached states by coverage instead of evicting the LRU tail
- [Intel GPU] Add opt-in decode graph capture widths for DSV4 on XPU
- [feat][NPU] Add not needs_cpu_seq_lens for dsa modules
- Docs
- Python not yet supported