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 stale multimodal padding after external hash overrides
- [Metrics] Add request-level TPOT histogram (sglang:request_time_per_output_token_seconds)
- fix converstions to int64 and handle negative page indices
- [diffusion] Extend Weight Cache Daemon to multimodal_gen
- fix: prevent silent overwrite on duplicate parameter tags in Qwen3CoderDetector
- [Bugfix] HiCache staged write-back: pass device-accessible destinations to cudaMemcpyBatchAsync
- [Qwen4-Exp] Add host staging for file-backed PLE
- [LoRA] Bound expert_id against num_experts in fused MoE LoRA kernel
- [Perf] Accept int64 array input_ids in TokenizerManager without re-copying
- [mem_cache] Trim out-of-window SWA slots when caching finished requests
- Docs
- Python not yet supported