PR #182 support autoround hpu format

support autoround hpu format #182

yintong-lu merged 18 commits into main from lyt/hpuint4

qlinear_hpu

eb0933cc

remove comments

324ebf35

yintong-lu marked this pull request as draft 1 year ago

Merge branch 'main' into lyt/hpuint4

7b6bf024

code change for post_init

62e77bfc

remove unnecessary log and add device arg for evaluation

8666f1fa

yintong-lu marked this pull request as ready for review 1 year ago

update readme

23527f18

update readme doc

9f4dff00

restore evaluation code

f37fed71

fix zp plus_1

36161c13

enable hpu inference of gptq models

9cf1602f

yintong-lu requested a review from

wenhuach21 1 year ago

wenhuach21 commented on 2024-07-15

change auto_quantizer logic

175db7a0

wenhuach21 commented on 2024-07-15

add ut and add qlinear_hpu_gptq

f764a761

wenhuach21 commented on 2024-07-16

wenhuach21 requested a review from

wenhuach21 1 year ago

wenhuach21 approved these changes on 2024-07-16

wenhuach21 commented on 2024-07-16

add hqt version check and refine doc

1b0fa750

comment qlinear_hpu

697b94e1

chensuyue added this to the 0.3 milestone 1 year ago

fix coverage issue

8d89d97e

fix coverage

5972c0f5

fix coverage

9795b23b

fix coverage

288c7914

yintong-lu merged 72f5ce80 into main 1 year ago

yintong-lu deleted the lyt/hpuint4 branch 1 year ago

Reviewers

wenhuach21

Assignees

No one assigned

Labels

None yet

Milestone

0.3

auto-round support autoround hpu format #182 Merged

support autoround hpu format #182

auto-round
support autoround hpu format
#182

Merged