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
- [NPU] Add debug nightly accuracy cases and first-run accuracy guard
- [Rust] Add API-key authorization to the embedded server
- [gRPC] Support standard health checks on the native server
- fix: prevent gloo same-group deadlock in prefetch progress check
- fix: use dynamic CU count instead of hardcoded 304 in tilelang DSA kernel
- [NPU] Optimize DFlash2 prefix KV writes and draft block preparation
- [PD] Add L2-Only decode-side radix cache for disaggregated HiCache
- [DeepSeek] keep pending q_a_proj/kv_a_proj_with_mqa halves across load_weights calls
- cp allgather rerange
- [KVCache] [DSV4] Add Direct INT4 KV cache with 29.27% higher token capacity.
- Docs
- Python not yet supported