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
- [NPU][DSV4] A5 explicit-state backend bring-up
- [NPU] linear ReplaySSM: ring decode via triton-ascend
- [Perf] [AMD] diffusion: Add opt-in MXFP8 attention on gfx1250 via aiter fmha_fwd_mxfp8_asm
- [CI] diffusion: replace FLUX.1/2 nightlies and add FLUX.3 TP2 e2e
- [Perf] sdar: Share block refresh with next-block denoising
- [Fix] multimodal: Gate caller mm_hashes behind --trust-caller-mm-hashes
- [NPU] Integrate CPU offload allocation and sampling uint32 fixes
- [Doc] muse-spark: document serving limits and GPU settings
- [Perf] [AMD] GLM5: Row-streaming KDA packed decode on gfx950
- [Feat] [AMD] kv-shard: Support KV cache sharding with aiter and MoRI
- Docs
- Python not yet supported