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] diffusion: LingBot-Video-MoE crashes in text encoding under default layerwise offload (tied vocab table on CPU)
- [Perf] [AMD] unquant: backport gfx11 weight-row padding (#46327) to amd_march
- fix: stream LFM2 Pythonic tool-call arguments incrementally
- [Fix] deepseekv3: stream tool-call arguments when the closing fence arrives with the name
- [Perf] [AMD] dsa: Row-split the DCP indexer, run owned sparse MLA on the aiter asm kernel, and pipeline the a2a
- [Perf] [NVIDIA] moe: Add the H200 FP8 per-channel Triton config for Beam-1.0 TP8
- [Fix] dflash: Apply the muP logit multiplier in DFlash2 and Domino draft heads
- [Fix] rust-server: Serve /v1/loads from every listener under multi-node DP attention
- [Feat] RL: Read byte ranges of output store fields into caller memory
- [CI] debug_utils: Set test_dumper nightly est_time from measured runs
- Docs
- Python not yet supported