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
- [Bug] Spark2.5 MLP uses tanh-approximate GELU instead of reference GELU
- feat(moe): support FlashInfer A2A with Triton runner
- Prevent scheduler crashes when Mamba checkpoint slots run out
- [Bug] `HarmonyParser` never flushes
- [Bug] `force_nonempty_content`: the answer stays stranded in reasoning_content when there's a single trailing space
- [Feature] Extend set_internal_state to hot scheduler knobs
- Fix two logging calls that drop their message
- [Bug] Ollama endpoints: /api/chat 500s on every request; /api/generate 500s when the client sends no num_predict
- [mem_cache] Add session_ids to KV cache events for disaggregated routing
- [ROCm][DSV4] Honor configured top-k backend in HIP radix
- Docs
- Python not yet supported