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
- [Refactor] multimodal: [sglang-miles] [MM refactor 4/9] Split feature transport and preprocessing placement out of the base processor
- [Fix] hicache: Reject host mappings that exceed NUMA capacity
- [Perf] [NVIDIA] muse-spark-open: Fuse MoE finalize with the 2shot_push all-reduce
- [CI] npu: Remove internal cache-service references from NPU workflows
- [Feat] [Intel] moe: Run --moe-a2a-backend mooncake on Intel XPU
- [Fix] Resolve dangling $defs refs in tool-call grammar schemas
- [Fix] sgl-kernel: bump sgl-attn to pick up FP8 two-level accumulation
- [Test] [XPU] kv_canary: Make kernel tests device-agnostic and run them on XPU
- [Fix] gemma4: Fix Bolt E4B and Gemma4 prefill CUDA graphs
- [Refactor] bcg: Record graph breaks at capture without running them
- Docs
- Python not yet supported