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
- [sgl-router] Render GLM-5.3 and GLM-5.3-Flash through sglang-processor
- [Performance] GGUF: dequantize + dense GEMM for large batches instead of MMQ
- [Fix] Preserve KDA prefill fallback for packed one-token batches
- feat(hicache): add indexed KVCR L3 storage with multi-pool restore
- [Fix] GGUF: IQ3_S codebook and q8_1 block sums
- [Perf] scheduler: Remove implicit CUDA syncs from Mamba extend scheduling
- [Perf] scheduler: Spread finished-request KV releases over decode steps
- [AMD] Use the preallocated EAGLE topk=1 draft chain on HIP
- fix(bench): Accept optional spaces in SSE data fields
- [Perf] [AMD] dsa: Run DSA prefill under breakable CUDA graphs on HIP
- Docs
- Python not yet supported