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
- Gdn fly dsl injection
- [Perf] Optimize SM120 FP8 blockwise decode GEMM
- Fix reader starvation after waiting writer cancellation
- [AMD] Enable gfx1250 AITER per-tensor FP8 FMHA for DiT
- Add NCCL M2N receiver for Miles weight updates
- [AMD][MiniMax-M3] Optimize the MXFP8 sparse decode kernel tail on gfx950
- fix: preserve streaming-session KV ownership in PD decode
- fix: preserve parent token modalities when appending session media
- [AMD] Quantize AITER unified prefill queries to FP8
- fix(quantization): handle unquantized MTP/NEXTN draft layers in compressed-tensors
- Docs
- Python not yet supported