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(quantization): defer compressed_tensors import (#10492)
- [Bug] Unbounded memory growth via orphan bootstrap_room injection leads to OOM Kill
- [Fix][DSA] transform_index: support non-2048 topk widths and guard out-of-range indices
- [Triton] Resolve TARGET_VERIFY query width from SpecInput.num_tokens_per_req
- [Bugfix] Reject unsupported Qwen3 and FA3 DCP configurations
- [Bug] [ROCm] MEM profiling crashes TP server in _dump_snapshot with RuntimeError: stoi
- [AMD][diffusion] Allow MiniMax-H3 full-loop denoise on ROCm
- Route MiniMax-H3 video VAE attention through AITER on ROCm
- perf(router): parse MCP response stream events once
- fix(hicache): back up chunked write-through inserts
- Docs
- Python not yet supported