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
- [Feat] glm5: Expose per-layer MLA key buffer and use_fused_topk in binding
- [Test] scheduler: Reset the published context after each prefill-adder test
- [Feat] disaggregation: Support shared Mooncake staging buffers for PD role switching
- [Bug] EPD encoder allocates unused pinned embedding pools on nonzero TP ranks
- [Bug] pause_generation(mode="abort") with --tokenizer-worker-num > 1 can let a request reach the scheduler after the KV cache is released
- [Fix] function_call: Stream Kimi K3 tool-call arguments incrementally
- [Feature] Add Host Offloading and Asynchronous Prefetching for DeepSeek V4.1 Engram
- [Bug] GLM-5.3 FP8 inference hangs after sustained workload with KV cache full (TP8, EAGLE, H200)
- [Feat] diffusion: let replicated ranks share the merge cache
- [Bug] GB300 aarch64/MNNVL: NCCL initialization fails under Nsight Systems in v0.5.22 stack
- Docs
- Python not yet supported