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
- [NPU] Add NpuSRTPlatform so current_platform resolves on Ascend
- [Bug] Two SM10x-gated cluster/tcgen05 kernels fail on B300 (sm_103): cutedsl TGV BF16 GEMM raises Xid 13 CGA "CTA Not Present", trtllm-gen MoE finalize hangs silently
- [Fix] Stream prose between and after DSML tool calls
- [Bug] [NPU] Router GEMM output should always be fp32
- feat: add layer-wise KV transfer for PD disaggregation
- [Bug] --enable-eplb + --speculative-algorithm DSPARK crashes during draft CUDA graph capture: on_select_experts scatter_add_ dimension mismatch (layer_idx=None)
- [Refactor]Benchmark: Make bench_serving benchmark args reusable
- [diffusion] Auto residency: per-pipeline containment fixes and CI baselines (4/4)
- [Bugfix] Kimi-K3: fix vision-DP rank-local indexing into global grid_thws_host
- [NPU] Support DSpark compact verify graph and folded verify epilogue
- Docs
- Python not yet supported