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
- Feature/npu mm global cache npu memcache
- [AMD] [Kimi-K3] Fix bf16 SSM decode under HIP graphs
- [AMD] fix: enable MiMo V2.6 MXFP4 on ROCm
- Main a5 pd
- [Observability] Propagate entry received_time through /v1/score and /v1/responses
- [Bug] Falcon-H1 with tied word embeddings cannot serve a single request, tied LM head's `.float()` upcasts the embedding in place
- [Bug] Aborting a constrained request while its grammar compiles returns HTTP 400 `BadRequestError`
- [Bug] `/generate` does not type-check its fields: one wrong-typed field takes the server down
- [Bug] wrong typed `session_params` field in one /generate request can crash server
- [Bug] `/abort_request` with a rid also aborts every request whose rid starts with it
- Docs
- Python not yet supported