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
- [Tracking] Host allocator: page-aligned allocation with host-side bookkeeping
- feat(npu): support Kimi K3 PCP with FLA affine states
- [Bug] Anthropic /v1/messages drops PD bootstrap fields during AnthropicMessagesRequest → ChatCompletionRequest conversion
- [LMCache] Support MLA/DSA dual-buffer KV cache in LMCache connector
- [NIXL] Fix O_DIRECT alignment and batch chunking for DSA indexer pool
- [Bug] qwen3.8-27b toolcall error
- test: cover invalid DeepSeek OCR ngram config
- [Bug] DSA top-k v2: tie-overflow selection is not exact — silently returns wrong top-k members (follow-up to #30512 / #30645)
- [Perf] Avoid full-logits all-gather for TP greedy sampling
- [AMD] Define gfx1250 QuickReduce stubs
- Docs
- Python not yet supported