PR #16550 Updating QDQ to support Float8E4M3FN

Updating QDQ to support Float8E4M3FN #16550

xadupre merged 39 commits into microsoft:main from xadupre:qdq

Updating QDQ to support float8 types

724b4af6

xadupre added quantization

github-advanced-security commented on 2023-06-30

lint

d99167ab

justinchuby commented on 2023-07-01

Merge branch 'main' of https://github.com/microsoft/onnxruntime into qdq

a566de15

improves quantization tests

409aea11

Merge branch 'main' of https://github.com/microsoft/onnxruntime into qdq

67b1fdfb

lint

603c0701

lint + bug

c9445602

Merge branch 'main' of https://github.com/microsoft/onnxruntime into qdq

eef744ed

github-advanced-security commented on 2023-07-12

justinchuby commented on 2023-07-12

fix quantization tests

05b6f313

Merge branch 'main' of https://github.com/microsoft/onnxruntime into qdq

b8621257

github-advanced-security commented on 2023-07-13

quantization

8531cf8d

better comments

46b39bbb

github-advanced-security commented on 2023-07-13

lint

ec21185f

Update quantization tool

5ac9e33c

Merge branch 'main' of https://github.com/microsoft/onnxruntime into qdq

ccec94d7

github-advanced-security commented on 2023-07-20

fix test for int, uint

8bbe3534

remove debug

47625fc9

github-advanced-security commented on 2023-07-20

lint

1a50b423

github-advanced-security commented on 2023-07-20

Fix quantization for bias

759cdc04

github-advanced-security commented on 2023-07-21

night commit

1b9fe1e7

still missing one step

54aace97

remove test on version

b0fd4123

github-advanced-security commented on 2023-07-22

lint

687a7afb

github-advanced-security commented on 2023-07-22

lint

a473cbf8

replace DequantizationLinear by Cast

6f6571dd

github-advanced-security commented on 2023-07-24

lint

fc0b6abf

github-advanced-security commented on 2023-07-24

fix QuantizeLinear for float16

cb394b15

fix qgemm

59cfb1b0

Merge branch 'qdq' of https://github.com/xadupre/onnxruntime into qdq

a09f085a

lint

54949ff2

lint

a97bdafd

github-advanced-security commented on 2023-07-24

fix unit test for quantization

f0625fc9

lint

216966fe

skip reference evaluator for one test

6982747f

fix misspelling used to debug

bd12e830

disable test when onnx not recent enough

e59bb7a4

github-advanced-security commented on 2023-07-25

fix remaining unit tests

f9dc10e5

xadupre marked this pull request as ready for review 2 years ago

github-advanced-security commented on 2023-07-25

lint

4c25922b

lint

987bf680

yufenglee commented on 2023-08-08

yufenglee approved these changes on 2023-08-08

xadupre merged d0316ee7 into main 2 years ago

xadupre deleted the qdq branch 1 year ago

Reviewers

yufenglee

justinchuby

github-advanced-security

Assignees

No one assigned

Labels

quantization

Milestone

No milestone

onnxruntime Updating QDQ to support Float8E4M3FN #16550 Merged

Updating QDQ to support Float8E4M3FN #16550

onnxruntime
Updating QDQ to support Float8E4M3FN
#16550

Merged