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
- [Feature] Add Host Offloading and Asynchronous Prefetching for DeepSeek V4.1 Engram
- [Bug] GLM-5.3 FP8 inference hangs after sustained workload with KV cache full (TP8, EAGLE, H200)
- [Feat] diffusion: let replicated ranks share the merge cache
- [Bug] GB300 aarch64/MNNVL: NCCL initialization fails under Nsight Systems in v0.5.22 stack
- [Perf] hicache: Reuse shared host indices within Mooncake offloads
- [Fix] scheduler: Preserve Mamba fork and tail states across chunked prefills
- [Feat] pp: Add CPU-staged Gloo transport for pipeline parallelism
- [Perf] dsv4: Dequantize eight V4.1 KV tokens per program in the sparse prefill gather
- [Perf] hicache: Add opt-in async ready-count sync
- [Fix] llava: Register native CLIP vision tower so LlavaForConditionalGeneration loads
- Docs
- Python not yet supported