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
- Stop adding omitted tool-schema fields to DeepSeek prompts
- [fa4] Fix FA4 for MLA prefill
- [Bug] DCP a2a backend NCCL crash at conc=64 (unhandled cuda error)
- Skip collective DeepEP Buffer destroy at interpreter exit (explicitly_destroy=True)
- [Bug] DSPARK/DFLASH spec v2 at page_size=1: req_to_token row too narrow for the decode reserve — silent KV slot leak at the context boundary
- [Spec] Size the req_to_token row for the DFLASH decode reserve at page_size=1 (fix DSPARK KV slot leak at the context boundary)
- Support prefill-side pipeline parallelism with EAGLE under PD disaggregation
- [DCP] Fix a2a backend NCCL crash on eager decode
- [Feature] Should we make the LM head GEMM output fp32 instead of bf16?
- [BUG] sunset Gemini Code Assist referenced in CI
- Docs
- Python not yet supported