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
- [Bench] fix mmmu multi image
- [WIP] Fuse shared expert gate into a single Triton kernel for Qwen MoE
- [refactor] Add opt-in get_compressor_state helper + document forward(**kwargs) aux-data contract
- [POC][MLU] Add in-tree MLU backend prototype
- [perf][Sampler] avoid fp32 intermediate in RL on-policy logprob
- Revert "[AMD] Fix stage-b-test-large-8-gpu-mi35x-disaggregation-amd"
- Revert "[AMD] ci: switch CACHE_HOST to a fresh path to fix "No space left on device""
- [test] add pure-PyTorch RoPE reference for jit kernel cross-check
- fix(disagg): group-aware MLA KV slicing for NPU NSA on mooncake backend
- Nemotron Perf Tracking
- Docs
- Python not yet supported