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
- fix(function_call): keep string-typed argument values literal in dots and Muse Glimmer
- [HiSparse] Split swap-in host->device copies into a wide copy_misses_kernel
- [AMD] MiniMax-M3: grouped-head shared-KV Triton verify and draft extend, plus Lean draft decode
- [Bug fix] moe_align_block_size: add the missing barrier before the expert_ids search
- [NPU] Fix packed MTP KV and Indexer transfers in HiCache
- feat(Qwen3.8-Flash-Next): avoid padded PLE prefill activations
- A question about SGLang and SGLang Omni
- [MPS][MLX] Capture single-request prompt logprobs in the exported region
- [Qwen4-Exp] aux-hidden capture at stage boundaries yields the hyper-connection-wide stream — intended width contract for consumers?
- [NPU] init npu backend before the parallel runtime touches a device
- Docs
- Python not yet supported