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
- fix: broadcast EAGLE draft-side sampling across TP ranks on ROCm
- [diffusion][AMD] Add support for new quantized attention backends for GFX942/GFX950
- fix: unblock the DSA prefill split-op graph surface on HIP (is_cuda gate)
- fix: guard top-logprobs and token-ids logprob rows against missing data
- [RFC] Orchestrator-facing Elastic EP lifecycle contract
- Fix stale batch fullness after chunked prefill
- [XPU] Bind sgl_per_tensor_quant_fp8/sgl_per_token_quant_fp8 on XPU
- fix: FA4 paged-KV zero-size page-table registers on SM90
- Fix output_dtype typo in block-wise quantization docstrings
- [Fix] : support MiniMax-M3 pipeline parallelism in PD disaggregation
- Docs
- Python not yet supported