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
- [Bug] Multimodal tensor views cause 518x pickle memory amplification
- [Bug] Fix multimodal pickle storage amplification
- [Bug] DSPARK compact ragged-verify (SGLANG_RAGGED_VERIFY_MODE=compact) crashes decode CUDA-graph capture on SM120: IMA in fused_norm_rope_v2 c4 compressor store
- [Fix] anthropic: report cumulative input usage on message_delta
- [Perf] DeepSeek-V4 dsv4 prefill on SM120 (4x RTX PRO 6000, TP=4): ~2-7K tok/s vs ~12.5K reported via vLLM/marlin on identical hardware — expected? tuning guidance?
- fix: handle heterogeneous Unlimited-OCR crop batches
- [Bugfix] Support MIS embedding overrides for Llama sequence classification
- [AMD] Fix Triton cache flooding in DSA and aiter backend (_get_valid_kv_indices_kernel)
- [PD] Fix spurious FINISH_LENGTH for requests aborted during KV transfer
- fix: support batched OpenAI cache keys
- Docs
- Python not yet supported