xla
Add int8 per channel weight-only quantized matmul
#7201

Merged

Add int8 per channel weight-only quantized matmul #7201

lsy323 merged 6 commits into master from lsiyuan/quant-ops

add quantized layers per channel

f7c200af

enhance tests, clean up

f48c666a

add q ops to ci

65f6fcab

add README

c042e2fa

lsy323 requested a review from

miladm 1 year ago

lsy323 requested a review from

JackCaoG 1 year ago

lsy323 marked this pull request as ready for review 1 year ago

lsy323 changed the title ~~Add int8 per channel quantized matmul~~ Add int8 per channel weight-only quantized matmul 1 year ago

update readme

878d7e78

lsy323 requested a review from

qihqi 1 year ago

JackCaoG commented on 2024-06-06

lsy323 added quantization

lsy323 requested a review from

JackCaoG 1 year ago

JackCaoG approved these changes on 2024-06-06

update readme

b4542372

JackCaoG approved these changes on 2024-06-06

lsy323 merged 56ddd5de into master 1 year ago

lsy323 deleted the lsiyuan/quant-ops branch 1 year ago

Reviewers

JackCaoG

miladm

qihqi

Assignees

No one assigned

Labels

quantization

Milestone

No milestone