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
- [Feature] Installing the required packages supports a certain range.
- [Feat] sgl-model-gateway: Accept bucket policy in the standalone CLI
- [Feat] [MUSA] fa3: Port production scheduler-metadata backend
- [Perf] kda: Write convolution output directly into contiguous QKV planes
- [Fix] trtllm_mla: Keep the fused fp8 KV write off a DCP-resolved loc
- [Feature] disagg: opt-in Rust wire-codec backend (sglang-disagg crate) for P/D data plane
- [Fix] rust-server: Serve decode_allocation_policy and enable_kv_cache_sharding from the bootstrap registry
- [Feat] [Intel] vmoba: Add XPU varlen attention path for VMoBA
- [CI] [AMD] release: release option for testing
- [Bug] DSPARK/DFLASH speculative decoding silently ignores repetition_penalty / frequency_penalty / presence_penalty
- Docs
- Python not yet supported