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
- [LoRA] Load PEFT ParamWrapper adapters for fused MoE experts
- [Fix] Fall back to observed CUDA coredump pipe name
- [MLU][CI] Add tests for the MLU CI ref resolver
- [DeepSeek-V4.1] Support indexer TP shard
- [Bugfix][PD] Accept slot_layer_ids in NixlKVManager.set_kv_buffer_tensors
- [LoRA] Fix cancellation and unload races during reference acquisition
- [KV Sharding] Integrate GLM DSA, MTP PD transfer and CPU HiCache
- [RFC][LoRA] Share a generation backbone with multiclass classifier heads
- [AMD] aiter target-verify: pass strided k/v to extend_attention_fwd without copying
- [NPU] MLA pool: index-K elision on A3, DCP pool fixes, short-pool warning
- Docs
- Python not yet supported