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
- [Fix] [XPU] graph: Retain capture inputs and reset graphs in FullXPUGraphBackend
- fix(expert_distribution): skip reset/append when _disable_all is True
- [Fix] hicache: Keep buffer-mode PP stages on PP0's drain and staging steps
- [Bug]
- [Fix] [AMD] JIT: Port per-token group FP8 quantization v2 to ROCm
- [Perf] radix cache: each eviction rebuilds a heap over all evictable leaves
- [Perf] [AMD] qsa: Share compressed-key reads across the four verify rows of a request on gfx950
- [Tracking] Predictable long-context agent serving: APIs, cache usage, and resource lifetime
- [Fix] scheduler: Support return_logprob with mixed chunked prefill
- [Fix] scheduler: Count buffer-mode prefetch hits in shortest-prefill-first
- Docs
- Python not yet supported