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
- [5/N][CP] Concentrate CP communication ownership in communicator
- Refactor: TRTLLMHAAttnBackend should not inherit from FlashInferAttnBackend when reuse is small
- Fix spec grammar overlap result ordering
- [WIP] Rust Unified Radix Cache (L1 only)
- [RFC] Generalize cuda_graph_* server args / runner naming to a device-agnostic scheme (device_graph_*)
- Make cur_batch/last_batch event-loop locals instead of Scheduler fields
- [RFC] Responses API fixes + Anthropic /v1/messages thinking block signature
- [AMD] Fuse bf16 kv_b_proj prefill epilogue via fused_gemm_a16w16_split_cat
- [Spec] Make `build_tree_kernel_efficient` enforce `seq_lens_sum` contract
- Fix ROCm causal Conv3D cat-pad fallback
- Docs
- Python not yet supported