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
- [RL] Flag the from_numpy sincos position tables as not weight-checked
- [Bugfix] Break InternVL tile-grid ties on area, not block count
- [CI] bot-cherry-pick: use a workflow-scoped push token and retry the push
- 【Fix】(hicache nixl): chunk oversized hybrid-pool transfers
- [Perf] Use set membership for id-existence check in _sort_tool_message_run
- [nixl staging buffer] fix decode hung issue when multiple chunks arrived out of order
- [AMD] perf(sgl-kernel) use the ROCm block_quota default for the MLA page_first KV write-back
- [AMD] perf(kernel): tune JIT HiCache transfer block_quota for ROCm
- [CI] Skip the GPU idle check on devices where NVML cannot report memory
- [Bug] pattern + minLength: xgrammar silently drops the length bound
- Docs
- Python not yet supported