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
- [MM] Harden Kimi image cache identity across preprocessing and radix hashing
- test(npu): add e2e test for DFLASH Domino
- [function_call]: keep MiMo string arguments literal
- [sglang-miles] Return sampling masks for chain EAGLE/NEXTN decoding
- feat(qwen4-exp): support GR and PLE sequence parallelism
- fix(npu): override quantization_config as null to protect indexer replay bf16 testcases
- Idle-wake hang at _low_ratio_index_topk_dense when --sleep-on-idle is enabled (post-#40111 prefill host-sync path)
- [Speculative] Add draft sampling overrides and retain corrected proposal probabilities
- [Simulator] Cache random text requests once
- perf(kv-cache): fuse sharded DSA indexer and raw FP8 stores
- Docs
- Python not yet supported