intel/auto-round

Pull Requests Commits
fix hpu typo (#30)
WeiweiZhang1 committed 2 years ago
Verified 6815f8b6
inc3 integration and refine export code (#28)
wenhuach21 committed 2 years ago
Verified cb49e91e
Add export format register (#27)
WeiweiZhang1 committed 2 years ago
Verified e24e4e46
Merge branch 'main' of https://github.com/intel/auto-round into main
WeiweiZhang1 committed 2 years ago
917ace75
fix typo
wenhuach21 committed 2 years ago
c2798a0b
add support matrix in readme (#26)
wenhuach21 committed 2 years ago
Verified 7caadac7
Refine readme (#25)
WeiweiZhang1 committed 2 years ago
Verified 4b0a0ba7
add example for gaudi2. (#24)
lkk12014402 committed 2 years ago
Verified afcd62f1
Merge branch 'main' of https://github.com/intel/auto-round into main
WeiweiZhang1 committed 2 years ago
fa2ae04e
Enable export without dir (#23)
WeiweiZhang1 committed 2 years ago
Verified b65830f3
Merge branch 'main' of https://github.com/intel/auto-round into main
WeiweiZhang1 committed 2 years ago
41b328c2
fix CI trigger branch (#21)
chensuyue committed 2 years ago
Verified 19e50da4
detect eval_legacy automatically (#20)
wenhuach21 committed 2 years ago
Verified 4f7878da
Support code scan in CI test (#19)
chensuyue committed 2 years ago
Verified 528252b9
force to fp32 tuning if amp is disabled and align sym quantization (#18)
wenhuach21 committed 2 years ago
Verified 3938d4ad
Refine quntization config (#17)
WeiweiZhang1 committed 2 years ago
Verified 2b821bca
fix typo
wenhuach21 committed 2 years ago
cf15c12e
add gemma-7b acc and shell info
wenhuach21 committed 2 years ago
1f79e54f
fix autogptq exporting issue at group_size=-1
wenhuach21 committed 2 years ago
eb0bb2d1
add shell and acc data for several models, fixed some issues
wenhuach21 committed 2 years ago
4ae7d455
Merge branch 'main' of https://github.com/intel/auto-round into main
WeiweiZhang1 committed 2 years ago
0557ed27
upgrade lm_eval (#14)
WeiweiZhang1 committed 2 years ago
Verified 440771c8
update accuracy section
wenhuach21 committed 2 years ago
3ff47860
fix typo
wenhuach21 committed 2 years ago
b81a5a55
rename export to save quantized (#15)
wenhuach21 committed 2 years ago
Verified 2fb6fd11
update readme (#13)
wenhuach21 committed 2 years ago
Verified a868c805
upgrade lm_eval
WeiweiZhang1 committed 2 years ago
6ba09c67
fix mixtral moe autogptq exporting issue (#11)
wenhuach21 committed 2 years ago
Verified 1869cde0
fix autogptq exporting issue
wenhuach21 committed 2 years ago
d413128f
fix autogptq exporting issue and update readme
wenhuach21 committed 2 years ago
b99431b0
Terms Of Use Privacy Policy Refund Policy Impressum