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
- test: verify git-cdn on NPU clusters
- [Diffusion] Fix Spectrum state reset for CFG-parallel branches
- perf: fuse FA3 query quantization with RoPE
- [diffusion][AMD] Add support for new quantized attention backends for GFX942/GFX950
- [Fix] Skip redundant routed_scaling_factor in TBO DeepseekV2MoE.op_output
- [Fix] DeepSeek-V3.1 streaming tool-call detector loses calls at chunk boundaries
- [AMD] DSv4/#34624: fire compress+norm+rope fusion under MTP (target_verify)
- [Bug] sgl-model-gateway fails Clippy due to needless borrows in cache-aware policy tests
- [Fix] Hold non-stream forced intermediate output on a stop-string prefix
- fix: remove needless borrows in cache-aware tests
- Docs
- Python not yet supported