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
- deps: align TileLang with Miles 0.1.14
- [Bug] json_schema accepts uniqueItems and multipleOf but does not enforce them
- [ROCm][QuickReduce] Q8 BF16→FP16 low-amplitude scale saturation attenuates all-reduce output
- Update to the cookbook for models supported by Intel Xeon CPUs
- Prefill CUDA graph reserves ~1.8 GB and starves quantized-KV long-context prefill on small cards (no auto-disable rule looks at free VRAM)
- dsv4.1: add numa_shared Engram host table layout
- [Fix] Preserve Chat/Responses logprob candidates and empty-delta records
- [Fix] Correct FlashKDA prefill return contract with regression tests
- [PD disaggregation] Duplicate client-supplied `bootstrap_room` crashes prefill and decode schedulers (uncaught `KeyError` / `ValueError`) # Checklist
- [Bug] [diffusion] MiniMax-H3 INT8 ConvRot checkpoints skip the head-interleaved QKV reorder, silently corrupting video/audio (same defect as #34227, non-FSDP path)
- Docs
- Python not yet supported