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
- [Bug] sgl-router (PD): open circuit breaker still dispatches to decode, producing a permanent fake-dead prefill
- benchmark: MI300X BF16 speed + accuracy data for Gemma 4 31B
- [DSA] Page-aware move_kv_cache for the DSA indexer cache (fix page_size>1 corruption)
- fix: truncate xgrammar accepted_tokens in place on rollback
- feat(flexkv): support hybrid cache with shared restore lifecycle
- [Perf] Support ragged verify graphs in the DSA attention backend
- [DSA] Add LiteTopk fused indexer top-k prefill path for SM100
- [Anthropic] Propagate tool_result.is_error into the rendered prompt
- [Fix] R-Fork remote_instance weight transfer defects
- [diffusion] feat: overlap declared-parallel pipeline stages
- Docs
- Python not yet supported