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
- [Feat] [NPU] speculative: support NGRAM decoding for MHA and MLA
- [Test] [AMD] deterministic: Add a TP2 deterministic inference test on MI35x
- [External Linker]Support prefetch interfaces
- [Feat] scheduler: Gate --prefill-decode-interval on running batch size
- [AMD][DSV4][2/8] fp8 verify: write the SWA ring in the fused norm/rope kernel
- [AMD][MoE][3/8] small-batch sort: histogram + bitonic sort for 32 < P <= 256
- [AMD][DSV4][5/8] FP4 indexer on aiter's row-group kernel for decode and target-verify
- [AMD][DSV4][6/8] optional e8m0 mxscale GEMM for dense 128x128 fp8 linears
- [AMD][DSV4][7/8] carry aiter DSv4 GEMM tuned rows and mHC tile_m=16 until aiter ships them
- [AMD] Small MoE sort: support the EP expert mask (stacked on #42498)
- Docs
- Python not yet supported