llama.cpp
llama : compute BERT graph with F16 K, V
#5891
Open
Overview
Commits
1
Changes
View On GitHub

llama : compute BERT graph with F16 K, V #5891

ggerganov wants to merge 1 commit into master from gg/bert-f16
ggerganov
slaren
ggerganov
slaren
iamlemec
ggerganov
iamlemec
slaren
ggerganov llama : compute BERT graph with F16 K, V
0ba20ed9
ggerganov ggerganov force pushed from 40ca2e03 to 0ba20ed9 1 year ago
ggerganov ggerganov added demo
mofosyne mofosyne added Review Complexity : High
ggerganov ggerganov marked this pull request as draft 106 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
No reviews
Assignees
No one assigned
Labels
demo Review Complexity : High
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum