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
- feat: Add DeepSeek V4 SWA recompute
- [Fix] Reject dynamic LoRA updates with tokenizer-worker-num > 1
- [Feature] Add build_app/init_app_state factory for embedding the OpenAI server in external ASGI hosts
- [Session] Finalize queued streaming-session turns on abort
- Fix mamba mem_cache tests on non-CUDA (XPU) devices
- support stream output for tools in qwen3.5
- [Fix] Cast state-pool indices to int64 in fused_recurrent GDN update kernel
- [Bugfix][HiCache] Fix allocator_type for decode in Mooncake standalone mode
- feat(disaggregation): prototype live P-to-D token handoff
- [fmha_v2] perf: use non-interleaved paged KV input for trtllm sm90/120 prefill
- Docs
- Python not yet supported