onnxruntime
Add quantization benchmark for transformer based model
#4482
Merged
Overview
Commits
11
Changes
View On GitHub

Add quantization benchmark for transformer based model #4482

yufenglee merged 11 commits into master from roli/quant_bm
yufenglee
yufenglee add support of quantization benchmark
e8104db9
yufenglee quantization benchmark
d817d58c
yufenglee add quantize.py
839959ce
yufenglee set threads immediate
e965d306
yufenglee enable to set thread num
9f0b5cca
yufenglee use ort package quantization
701fdab1
yufenglee merge quantize option and fp32/fp16 options
9c2e0ea9
yufenglee add comments
dd55e5af
yufenglee yufenglee requested a review from liuziyue liuziyue 5 years ago
yufenglee yufenglee requested a review from tianleiwu tianleiwu 5 years ago
yufenglee yufenglee requested a review 5 years ago
yufenglee format style
25cea437
yufenglee refine comments
57c39131
tianleiwu
tianleiwu commented on 2020-07-10
tianleiwu
tianleiwu commented on 2020-07-10
yufenglee remove useless code
db1f4ded
tianleiwu
tianleiwu commented on 2020-07-11
tianleiwu
tianleiwu approved these changes on 2020-07-13
yufenglee yufenglee merged 3d4ac851 into master 5 years ago
yufenglee yufenglee deleted the roli/quant_bm branch 5 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum