decoding_attention icon indicating copy to clipboard operation
decoding_attention copied to clipboard

Published 20 hours ago • verified publisher icon Bruce-Lee-LY
→

Metadata

Decoding Attention is specially optimized for multi head attention (MHA) using CUDA core for the decoding stage of LLM inference.

Results 0 decoding_attention issues
Sort by recently updated
recently updated
newest added

← Metadata

17
Stars
1
Forks
Watchers

Owner

verified publisher icon Bruce-Lee-LY

Metadata

Decoding Attention is specially optimized for multi head attention (MHA) using CUDA core for the decoding stage of LLM inference.

Back