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
- [DCP] Add GLM-5.3 Flash EAGLE/MTP support
- [DSV4.1][PD][8/N][Perf] Fuse candidate selection and masking for DeepSeek V4.1 prefill
- [Scheduler] Reclaim the idle device cache on every rank
- [dsa] drop the hardcoded topk==2048 assert in the prefill index transform
- [Docs] Add Ascend NPU (Atlas 800I A3) deployment scenarios to the Kimi-K2.6 cookbook
- [Kernel] Make the split-K FP8 reduce kernel M-independent to stop serving-time recompiles
- fix(spec): sync grammar state for mixed decode tails
- [Bug] handle_embedding_request does not abort over-length requests before enqueuing
- [Fix] Preserve list and tuple sharding in interleave CP
- [diffusion] scheduler: keep edit batches source-safe
- Docs
- Python not yet supported