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
- [JIT] Fuse FP8 KV-cache quantization into the prefix-valid commit kernel
- Router build combine 20260922
- [Bug] /v1/responses: accepted `xhigh` reasoning effort aborts the stream inside ResponseCreatedEvent
- Fix /v1/responses stream abort when reasoning effort is xhigh/max/none
- [Bug] Sglang 0.5.17 crashing with the following stack trace
- [Bug] v0.5.19 can't decode image
- [Bug] v0.5.19 tokenizer hang
- feat(dsv4): route A5 compressor to explicit SWA-mapped state table
- [Feature] Forward unknown tool calls by default; the parse-time drop kills agent loops
- [Perf] Extend Kimi K3 GEMM/all-gather to the speculative verification front
- Docs
- Python not yet supported