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
- [PD] Slice appended hybrid draft KV across heterogeneous TP
- [rust-processor] share model file resolution logic
- [NPU] [quantization] support NZ for w4a4 linear
- [DFlash] Feed committed tokens to the penalizers (repetition/frequency/presence/min_new_tokens)
- [HiCache][PD] Allow DSA index-K elision under HiCache and disaggregation
- [DSA] Q8KV8 FP8 Sparse Prefill on GLM-5.3-Flash with BF16 KV Cache
- [AMD][Quark] Kimi K3 Quark FP8/MXFP4 fusion
- Improve total prefix cache tokens available when using hicache + write back
- [AMD][gfx95] GLM-5.3-Flash MXFP4 MoE decode: small-M kernel and sort-fused FP4 quant
- [AMD][Perf] Quantize the BF16 shared expert of Quark MXFP4 checkpoints to MXFP4 while loading for shared-expert fusion
- Docs
- Python not yet supported