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] sglang:kv_cache_memory_usage_gb reports 0 for DeepSeek-V4 pools
- feat(cache): expose hybrid cache observability
- [Spec][Ngram]: Add country-card and distractor corpora to benchmark global tree allocation
- [Kernel] Make KDA backend dispatch hardware- and shape-aware
- [PDMux] scheduler event loop deadlocks in decode_stream.synchronize() when a mixed decode+split-prefill batch follows a >=4K-token prefill (hybrid GDN models)
- [Speculative Decoding] Add native UNO of linear verison serving supprt for NPU
- [Bug] [Rust gateway] reasoning_effort: support full OpenAI 7-tier set (blocked on smg release)
- [diffusion] Plan component residency from calibrated warmup records (2/4)
- [diffusion] Apply, validate and roll back calibrated residency after warmup (3/4)
- [Fix] function_call: stream "{}" for zero-argument tool calls in the base detector
- Docs
- Python not yet supported