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
- [Bug] AutoRoundConfig ignores packed_modules_mapping and hf_to_sglang_mapper, breaking two AutoRound checkpoints
- Drop the GLM-5.3-Flash breakable prefill chunk-size pin
- [DeepEP] Ship static-FP8 W4AFP8 normal dispatch in a BF16 view
- [Bug] Scheduler stalls with no running requests because batch_is_full is not reset (v0.5.20)
- Enable XPU in host KV cache pool for MHA and Mamba
- [CPU] enable grok-2 and wait refine
- [AMD][Kimi-K3] Take the aiter fused cat+cache path on NoPE MLA layers on gfx95
- [Fix] MiniMax-M3 boots again with its default tc_piecewise prefill graph
- [Model] Support XLMRobertaForMaskedLM and BertForMaskedLM as embedding models
- [ROCm] Add DeepSeek-V4 Pro FP4 Triton Gluon decode MoE
- Docs
- Python not yet supported