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
- [EPLB] Skip expert-distribution pass boundary during CUDA-graph capture
- Fix ReDoS in PythonicDetector's tool-call locator regex
- [Feature] Skip redundant DeepGEMM all-M warmup when a compatible JIT cache is restored
- Resolve per-GPU IB device for remote-instance P2P weight loading
- [attention] Fix broken nsa_backend backward-compat shim (ImportError)
- [NPU] Support DeepSeek-V4 on A2
- [docs] Fix inconsistent MOONCAKE_PROTOCOL supported values and default
- [disaggregation] Mooncake: report KV transfer latency metric and set KVPoll.Transferring
- Fix flush_cache() no-op after pause_generation(mode="retract")
- [Activation] Use FlashInfer silu_and_mul on SM120+ for 1.49x speedup
- Docs
- Python not yet supported