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
- [HiCache] Keep the backup worker alive on storage backend failures
- [Bug] HiCache backup thread dies on any storage backend exception; queued backups and their host memory are never released
- fix(hicache): emit BlockStored(CPU) event in UnifiedRadixCache insert…
- Enable compact GLM NoPE KV storage with native FlashInfer
- [CI][Intel CPU] Register nightly-intel-cpu-gnr suite and set est_time for registered tests
- Feat/cuda graph tensor dump
- [NPU] Dspark compact
- Fix DeepGEMM import for independently enabled MHC prenorm
- [Kimi-Linear] declare packed_modules_mapping and HF-faithful MoE prefixes so compressed-tensors ignore lists apply
- [Bug] HiCache: prefill forward stalls behind the entire host-to-device load burst because round-head H2D copies are issued after the burst hand-over
- Docs
- Python not yet supported