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
- [DSA] Reject backends that cannot serve index_kpool > 1 at arg resolution
- [ROCm][Perf] Quantize the BF16 shared expert of Quark MXFP4 checkpoints to MXFP4 while loading for shared-expert fusion
- [AMD][MoE] small-batch sort: histogram + bitonic sort kernel for 32 < P <= 256
- [AMD][DSv4] Emit the fused shared-expert slot from the sqrtsoftplus router gate
- [CI] Remove duplicate MUSA registration entries
- [AMD][DSV4] Reuse q_lora fp8 quant for the C4 indexer wq_b
- [AMD][DSV4] route bf16->fp32 GEMM to aiter's tuned FlyDSL kernel
- [AMD][DSV4] fp8 verify: write the SWA ring in the fused norm/rope kernel
- [Diffusion] MiniMax-H3 fuse the video VAE decoder's RMSNorm and QK RoPE
- [HiCache] Isolate TP-sharded Mamba state in file storage
- Docs
- Python not yet supported