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
- [dLLM] Don't cache the in-flight denoise block in the radix tree
- [Playground] Verified cell: dgx-spark / default / nvfp4 / undefined / single
- [Bug] Ranks sharing one `ssd_offload_path` collide on Mooncake bucket files → L3 cache broken
- [Bug] TP>1 LoRA tensor hot-load reuses one-shot ForkingPickler FDs and crashes schedulers
- [Fix] Forward unknown InternLM tools when configured
- [mem_cache] SWA radix cache: evict branch tail sliding window last
- [Responses] Fix max_output_tokens overestimate on multimodal requests
- Fix: omit null id/name in streaming tool call deltas
- Qwen-VL: literal vision marker in text is parsed as extra image when request contains an image
- [npu] [bugfix] fix mambacache & fused ops
- Docs
- Python not yet supported