flash-attn

Here are 5 public repositories matching this topic...

对数注意力（Logarithmic Attention, LogA）的官方实现，对数级别的计算复杂度。

vit loga flash-attn

用 pytorch 模拟实现 flash_attn v1/v2 的核心算法

pytorch llm flash-attn

Compile environment for Pytorch with CUDA

python cloud compiler docker-image cuda python3 pytorch jupyterlab cuda-toolkit code-server flash-attn sage-attention

A list of uv environments templates for LLM development.

python environment deep-learning conda pytorch venv uv llm flash-attn verl openrlhf

🌐 Streamline LLM development with ready-to-use environment templates for efficient setup and deployment.

python environment deep-learning conda pytorch venv uv llm flash-attn verl openrlhf

Add a description, image, and links to the flash-attn topic page so that developers can more easily learn about it.

To associate your repository with the flash-attn topic, visit your repo's landing page and select "manage topics."