Skip to main content
2 votes

Batch wise Inference to speed up Muzero's MCTS

Batching: A Good Idea You're right, batching is a great way to speed up AlphaZero or MuZero self-play! Your proposed solution of running multiple games in parallel is the easiest way to achieve some ...
KarelPeeters's user avatar
1 vote

Is the multi-headed projection matrix in self-attention redundant?

The technical reason is the residual connection around the self-attention block (first line in your code: x += self_attention(x)). The transformation $W_O$ is ...
Chillston's user avatar
  • 1,748
1 vote

How can a LLM optimise on it's own processing speed

It is not currently possible to directly give a large language model access to measure the time it takes to generate its answers and optimize on that. The model's response time is largely determined ...
Ari Setiawan's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible