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
- [AMD] Disable fused RoPE KV path on gfx1100
- Return the existing error for missing weight-export groups
- [Kernel] Fused Triton gather + dequant for ModelOpt NVFP4 embeddings
- Reject disabled expert recorder controls before scheduler dispatch
- [Fix] Apertus2509Detector: keep parsing the buffer after emitting a tool block
- [Fix] Discover the SiMM process NUMA node beyond node zero
- feat(sglang-miles): add ModelExpress S3 weight refit
- [BugFix] Drain pending NGRAM inserts before resetting the online cache
- [BugFix] Reject LoRA loads before exceeding pinned adapter capacity
- [Fix] Honor no-special-token encoding in native chat requests
- Docs
- Python not yet supported