onnxruntime
Add GQA on CPU in LLaMA scripts
#20720
Merged

Add GQA on CPU in LLaMA scripts #20720

kunal-vaishnavi
kunal-vaishnavi Add changes to support GQA for CPU
fc92f7a8
kunal-vaishnavi Enable trusting remote code
10750bc2
kunal-vaishnavi Set pad token id to EOS token id
4e0738b9
tianleiwu
tianleiwu commented on 2024-05-18
tianleiwu
tianleiwu dismissed these changes on 2024-05-18
kunal-vaishnavi Add GQA for FP32 CPU during optimization
115b8cad
kunal-vaishnavi Enable trusting remote code via authentication
8051ef76
kunal-vaishnavi Add changes suggested by linter
f0ba1f01
kunal-vaishnavi kunal-vaishnavi dismissed their stale review via f0ba1f01 1 year ago
kunal-vaishnavi kunal-vaishnavi changed the title Add support for GQA on CPU in LLaMA benchmarking scripts Add GQA on CPU in LLaMA scripts 1 year ago
github-advanced-security
github-advanced-security commented on 2024-05-18
tianleiwu
tianleiwu approved these changes on 2024-05-18
hanbitmyths hanbitmyths merged 72a3bde3 into main 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone