20250173561. Tuning Large Language Mo (QUALCOMM Incorporated)
TUNING LARGE LANGUAGE MODELS FOR NEXT SENTENCE PREDICTION
Abstract: a processor-implemented method includes generating a group of single-head attention (sha) operations based on a number of attention heads in a multi-head attention (mha) mechanism, each sha operation corresponding to a respective attention head of a group of attention heads associated with the mha mechanism. the method also includes parallelly executing each of one of the group of sha operations independently between hardware blocks of a device associated with a neural network model. the method further includes generating an mha output based on parallelly executing each of one of the group of sha operations.
Inventor(s): Carl Alexander BLACKLOCK, Sahil GUPTA, Veluppillai ARULESAN, Jeffrey Baginsky GEHLHAAR, Kanghwan JANG, Pranav SHRESTHA, Hariharan SUKUMAR, Jian WANG
CPC Classification: G06N3/08 (Learning methods)
Search for rejections for patent application number 20250173561
- Patent Applications
- QUALCOMM Incorporated
- CPC G06N3/08
- Carl Alexander BLACKLOCK of Toronto CA
- Sahil GUPTA of San Diego CA US
- Veluppillai ARULESAN of Concord CA
- Jeffrey Baginsky GEHLHAAR of San Diego CA US
- Kanghwan JANG of San Diego CA US
- Pranav SHRESTHA of San Diego CA US
- Hariharan SUKUMAR of San Diego CA US
- Jian WANG of Thornhill CA
