attention-by-hand

attention-by-hand

rukenx

Transformer attention, worked through numerically; from self-attention and RoPE to KV cache, MQA, and GQA.

1 Stars
0 Forks
0 Watchers
Python Language
30 SrcLog Score
Cost to Build
$11.6K
Market Value
$4.7K

Growth over time

2 data points  ·  2026-08-30 → 2026-09-26
Stars Forks Watchers
💬

How do you feel about this project?

Ask AI about attention-by-hand

Question copied to clipboard

What is the rukenx/attention-by-hand GitHub project? Description: "Transformer attention, worked through numerically; from self-attention and RoPE to KV cache, MQA, and GQA.". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone attention-by-hand

Clone via HTTPS

git clone https://github.com/rukenx/attention-by-hand.git

Clone via SSH

[email protected]:rukenx/attention-by-hand.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the attention-by-hand issue tracker:

Open GitHub Issues