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
- feat(hicache): opt-in exclusive L2->L3 tiering, dedup cache-mode L3 writes through the existence cache
- [1/N] Introduce a Fault-Tolerance Framework for SGLang
- [kv-shard 3/4] Enable Control Plane C
- [Unified Cache] Support out-of-tree external linkers
- [Bugfix] Fix route Ascend FuseEP through DeepEP path in MiniMax-M3
- [JIT] Fuse FP8 KV-cache quantization into the prefix-valid commit kernel
- [AMD][Bugfix] Route default aiter NEXTN draft extend off the faulting CK kernel
- fix(inkling): return 400 instead of 500 for unfetchable/undecodable multimodal input
- [GLM47] Reduce full-assistant grammar overhead: batched masks, thinking fast path, shared metadata
- [Bugfix] Detokenizer: keep sent_offset monotonic when a character is split across steps
- Docs
- Python not yet supported