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
- [Bug] MiniMax-M3 incorrectly routes Ascend FuseEP through the normal MoE path
- [RFC] Engine initialization snapshots: CRIU-based create/restore to skip engine startup
- fix: preserve input embeddings in session requests
- [WIP][rust-server] dedup `sampling.rs`
- [Bug] `qwen3_coder` non-streaming parser drops visible text after a valid tool call
- [Bug] DSV v4.1 Flash 2x4 H200 TP8/EP8 + DSPARK causes startup deadlock after DSpark draft weight load on dev-cu13-dsv41 and latest dev-cu13 image
- fix darft fias-v2 branch when fias v2 on
- [HiCache] Avoid over-eviction by reclaiming only allocation shortfalls
- [Bugfix] Fix route Ascend FuseEP through DeepEP path in MiniMax-M3
- [diffusion] LTX-2: skip self-attention mask so fused attention runs
- Docs
- Python not yet supported