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
- [CI] [AMD] memory_pool: Keep separate K/V allocations on ROCm to fix Mooncake PD accuracy
- [Perf] [AMD] gfx1151: Add Triton configs for Qwen3.5 AWQ MoE
- [Fix] [AMD] docker: Update Mooncake for HIP RDMA memory accounting
- [Perf] [AMD] glm5: Tune sampling, shared-expert fusion, and DSA kernels
- [Perf] [AMD] qwen4_exp: Fuse hyper-connection combine, norm and mix
- [Feat] grpc: Advertise media inputs in GetServerInfo
- [Chore] [AMD] docker: Build uTLX into the gfx950/gfx1250 rocm10 images
- [Perf] hicache: Publish prefill read-done when offload copies are fenced on the forward stream
- [Perf][DSA]: Capture DSA prefill attention and the NextN draft prefill in the prefill CUDA graph
- [CI] diffusion: Run test_image_preprocessing in the diffusion unit suite
- Docs
- Python not yet supported