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
- [BugFix]: Add JSON schema depth and state bounds validation to prevent Potential DFA state explosion and CPU thread hanging in JSON Schema grammar compilation under deeply nested schemas
- [Bugfix][AMD] Fix memory access fault and update document
- [AMD] Update Wave attention backend
- KeyError: 'model.layers.14.mlp.shared_expert.gate_gate_up_proj.weight'
- [Roadmap] sglang auto tuner
- [AMD] Feat/aiter ck gemm server argument
- [Feature] Enable DeepSeek V4 index cache
- [HiCache][Observability] Add fine-grained L1<->L2 KV transfer metrics (events / blocks / bytes / duration / bandwidth)
- [SPEC] feat: add throughput-aware policy for cost-guided adaptive speculative steps
- [Bug] GLM-5.2-NVFP4 error on pro6000
- Docs
- Python not yet supported