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
- [Fix] scheduler: Keep the new-token ratio at its floor after a KV-full retraction
- Feat/npu dsa tree verify
- [Fix] scheduler: Reap HiCache events while the engine is paused
- [Feat] spec: Add a topk=1 chain target-only sampling kernel
- [Fix] DFLASH: Reuse length buffers for unindexed CUDA devices
- [Bug][MUSA] fa3: scheduler metadata is computed from the draft backend under speculative decoding, hanging when the radix cache hits
- [Feat] [CPU] kernel: add chunk_kda kernel for xeon cpu
- [Feat] [XPU] add xpu api support for fused_inplaced_qk_norm and fused_qknorm_rope_out_of_place
- [Fix] [Intel] qwen4_decode: Import CustomAllReduceV2 lazily
- [Perf] [AMD] diffusion: add a Triton dense attention prefill path for gfx1151
- Docs
- Python not yet supported