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
- [DSA] Enable sparse MLA decode+prefill on SM120/SM121 (consumer Blackwell) via flashinfer's packed sparse backend
- [multimodal] Decode input_audio media containers with PyAV
- [Spec] Support DSPARK in disaggregation decode mode
- [LoRA] Size column-parallel LoRA-B buffers via an output-axis shard probe
- [LoRA] Skip LoRA wrapper modules in post-load quant weight processing
- [LoRA] MoE-LoRA CUDA-graph fixes under DP attention + RL adapter-reload fixes
- tmp
- [Fix] Simple fix: pass tokenizer stop tokens to XGrammar so constrained requests can terminate
- [1/N] [spec] align draft-extend graph-replay buckets with can_run_graph
- [Docker] Bump DEEPEP_COMMIT past hidden-dim-3072 support (pre-EPv2 tip)
- Docs
- Python not yet supported