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
- [CI] check-pr-test-health: Retry transient GitHub API errors
- [Fix] openai: replay gpt-oss reasoning_content as thinking for tool-call turns
- [Fix] diffusion: Validate config file root types
- [Fix] disagg: Bound Mooncake registration decoding
- [Fix] multimodal: expand2square must return RGB for every PIL mode
- [Fix] dspark: Hand the overlap readback a snapshot of the folded accept, not views (#42465)
- [Perf] [NVIDIA] muse-spark: Fuse the o_proj all-reduce into the attention boundary
- Strict tool constraint fails the whole request when one tool schema does not compile
- qwen3_coder structural tag triggers on the text `<tool_call>\n<function=`; use the `<tool_call>` token (xgrammar token_markers)
- [Perf] diffusion: Fold the Cosmos3 audio tokenizer weight norm at load
- Docs
- Python not yet supported