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
- [Perf] Drop unguarded message deepcopies; summarize tools in level-2 request logs
- [Fix] kvcache: Skip the reserved padding slot in the zero-RoPE MLA KV writer
- [Perf] [AMD] qwen3.5: Fuse decode KV write, seg plan and cu_seqlens a…
- [Perf] pd: Poll finished KV transfers while the prefill loop waits for a forward result
- [Feat] [Intel] kernel: Add Conv1D kernel for CPU
- [Perf] Cache the serialized tool-call constraint across requests
- [RFC] Decouple Scheduler Control from Forward Submission
- [Fix] dflash: Apply request penalties under DFLASH and DSPARK
- [RFC]: Quota and global-eviction contract for HiCache L3 when the backend is a shared filesystem
- [Diffusion] Fuse Joy image MLP GELU on SM120 in high quality
- Docs
- Python not yet supported