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
- Support Structured Outputs with enable_thinking=False in Qwen3
- [VLM] Refactor video processing to fully async mode
- Integration with elasticmem
- Fix potential race condition in shm_broadcast.py and unify socket cre…
- [fix][PP][NPU] Fix garbled output with concurrent DeepEP and PP
- Eliminating IPC Overhead with Free-Threaded Python
- [Speculative] Add DFlash speculative decoding for the MiMo-V2.5 Pro MXFP4 target
- [BugFix] Fix int32 overflow in MoE topk and concat_mla indexing
- [GDN] Add MTP cache mode for final-state recompute, with FlashInfer kernel integration and overlapped CUDA-graph state recovery
- feat(mem_cache): semantic KV cache reuse via a pluggable fuzzy-match radix backend
- Docs
- Python not yet supported