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
- [draft] [feat][AMD]Minimax-M3-mxfp4: share index top-k with a repeating pattern
- [AMD][DSv4.1] Use the fused Triton router for VL routing on ROCm
- [Feat] simulator: migrate the estimator SDK to AISimulate
- Fix Qwen3.8 CPU decode regression under torch compile
- [Feat] [NPU] cp-decode-attn-tp: Support dynamic ModelSlim W8A8 weights
- [Fix] spectrum: bound Spectrum under FLUX.1 true CFG and cap CFG gate reuse
- [Refactor] attention: TRTLLMHAAttnBackend inherits from AttentionBackend directly
- [Fix] moe: Fix --enable-fused-moe-sum-all-reduce outside CUDA and with LoRA hooks
- [Fix] auth: Require admin API key for weight update endpoints
- [Perf] [AMD] mimo-v2.6: Fuse small-M QKV projection on gfx950
- Docs
- Python not yet supported