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
- [diffusion] cache: add DPCache, calibrated key-timestep caching
- [AMD] fix: Wan2.2 crash due to Triton kernel compilation
- [Diffusion] Sensenova bf16 rope npu main
- [AMD] Use packed AWQ GEMM for small batches
- [AMD][Bugfix] Route default aiter NEXTN draft extend off the faulting CK kernel
- retest dsv4 on a5
- [DeepSeek V4.1] Support encoder-only prefill for PD disaggregation
- [AMD] Add gfx1250 MI45x ci/cd
- [NPU] Fix W4A8 MoE scale_bias sharding for tensor parallelism
- [Fix] Reject Chat Completions streaming errors in bench_serving
- Docs
- Python not yet supported