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] MiniMax-M3 W4A16 (compressed-tensors) on 2x DGX Spark (sm_121, TP=2): serves but every token is id 0 — all-NUL output on the Triton MiniMaxSparse path; same weights correct on vLLM
- Time out decode preallocation waits and clear stale lifecycle state
- [MLX] Dispose of retracted request state at retract time (fixes #33547)
- fix(qwen4): disable mixed-chunk with compressed QSA + fail-fast guard
- [Bug] transformers pin (5.12.1) incompatible with main: import sglang fails on both sides of the version line
- [Spec] Budget the DFLASH/DSPARK draft KV pool by attn_tp_size, not tp_size
- [MoE] Support NVFP4 dispatch with standard FlashInfer TRTLLM and CuTe DSL backends
- [Intel GPU] Disable FP8 W_o/A GEMM on XPU where DeepGEMM JIT cannot build
- Query free device memory through the active accelerator in triton_load_watch
- [Intel GPU] Map the generic profiler activity to XPU on Intel GPUs
- Docs
- Python not yet supported