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] hicache: retain prefetched host pages until admission
- [Doc] sampling_params: Improve `/generate` Http Native API documentation
- [Feat] [Apple] simulator: Support single-worker Replay simulation on macOS
- [Refactor] cleanup: Prune dead code and env vars, fix silent failures found by the code-cleanup skill
- [Fix] scheduler: Do not finish ignore_eos requests on grammar termination
- [Feat] [NPU] DSpark: Support multi-stream execution in draft layers
- [Feat] paged-experts: a disk tier for experts that do not fit host memory
- [Perf] [NVIDIA] kda: Use 8-row value tiles for the FP32-state packed decode on SM90 and SM10x
- [Perf] rust-server: Bound log-string truncation to the kept prefix and suffix
- [Perf] kv_canary: Batch active slot D2H transfer and SWA LUT translation in KV canary perturb
- Docs
- Python not yet supported