Pinned Loading

1. flash-attention flash-attention Public

   Forked from ROCm/flash-attention

   Fast and memory-efficient exact attention

   Python

2. nano-vllm nano-vllm Public

   Forked from GeeeekExplorer/nano-vllm

   Nano vLLM

   Python

3. snowflakedb/ArcticInference snowflakedb/ArcticInference Public

   ArcticInference: vLLM plugin for high-throughput, low-latency inference

   Python 280 37

4. Repeerc/flash-attention-v2-RDNA3-minimal Repeerc/flash-attention-v2-RDNA3-minimal Public

   a simple Flash Attention v2 implementation with ROCM (RDNA3 GPU, roc wmma), mainly used for stable diffusion(ComfyUI) in Windows ZLUDA environments.

   Python 48 7