vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][KV Connector] Fix incorrect recompute on KV-load-failure recovery (sync + async)
- [Bug]: [Performance]: Qwen3-VL-32B-FP8 throughput collapses on v0.25.1 (v0.24.0 fine)
- [Bugfix][Spec Decode] Inherit target KV cache scales in Gemma4 MTP draft layers
- [Bugfix][Hardware][AMD] Handle AITER unified-attention LDS overflow with Triton fallback
- [Bugfix] Make metadata send non-blocking in GroupCoordinator.isend_tensor_dict
- [Feature]: MoE router GEMM with the HPC-Ops bf16xfp32 kernel
- [RFC]: Multimodal Asynchronous Collaborative Architecture Sidecar
- [Bug]: [kernel] MRotaryEmbedding Triton kernel hardcodes Neox-style rotation, producing wrong results for GPT-J style models (like GLM-OCR).
- [mooncake] support CUSTOM_MEM_POOL in vllm
- [XPU] Support Sequence Parallelism for mxfp8 on XPU
- Docs
- Python not yet supported