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
- [Qwen3.5] Add TBO support for Qwen3.5
- fix: preserve background flag when slicing requests
- [Fix] Guard None mamba_next_track_idx in set_mamba_track_indices_from_reqs
- [NPU] Fixed the failed test cases of the nightly build on June 5.
- [bench] Reduce SSE overhead for large batch sizes in bench_one_batch_server
- [RL] Add explicit weight post-processing hook
- [Bugfix] Keep dataset-specific benchmark result args accurate
- [Draft] Introduce RuntimeContext (PoC for consolidating process-level global state)
- Fix DLLM rollout sampling diversity and expose decoding step maps
- Fix multi-tokenizer batch IPC routing
- Docs
- Python not yet supported