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
- [Doc] cookbook: Label non-GPU benchmark throughput per chip
- [Perf] dsv41: Add an opt-in current Mega prefill kernel
- [Fix] disaggregation: Reject PD pairs whose DSA KV rows differ in width
- [Refactor] multimodal: [MM refactor 4/9] Split feature transport and preprocessing placement out of the base processor
- [Refactor] multimodal: [MM refactor 5/9] Add a token-space multimodal processor
- [Refactor] multimodal: [MM refactor 6/9] Serve token-space processors behind --enable-token-space-processor
- [Refactor] multimodal: [MM refactor 7/9] Add a token-space strategy for Qwen VL models
- [Refactor] multimodal: [MM refactor 8/9] Check token-space Qwen output against the legacy processor
- [Refactor] multimodal: [MM refactor 9/9] Expand only the new turn of a multimodal request
- [Doc] tool-parser: Document every registered tool-call parser and test the table
- Docs
- Python not yet supported