intel/auto-round

Pull Requests Commits

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 174 days ago

42f6aa60

Merge branch 'enable_mxfp_exporting' of https://github.com/intel/auto-round into enable_mxfp_exporting

WeiweiZhang1 committed 174 days ago

6eb5f4be

rm torch_compile from nvfp funcs

WeiweiZhang1 committed 174 days ago

2d411b70

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 174 days ago

f6045620

Merge branch 'enable_mxfp_exporting' of https://github.com/intel/auto-round into enable_mxfp_exporting

WeiweiZhang1 committed 174 days ago

cf63235b

WeiweiZhang1 committed 174 days ago

c362c1d8

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 175 days ago

e6eaa633

WeiweiZhang1 committed 175 days ago

12455cf2

Merge branch 'enable_mxfp_exporting' of https://github.com/intel/auto-round into enable_mxfp_exporting

WeiweiZhang1 committed 175 days ago

624b82be

WeiweiZhang1 committed 175 days ago

48bd1006

Merge branch 'main' into enable_mxfp_exporting

WeiweiZhang1 committed 175 days ago

Verified 7a5c9a06

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 175 days ago

cc87eb08

refine export, fixtypo, add UT

WeiweiZhang1 committed 175 days ago

a0dd6cef

fix gguf mistral_common import (#736)

n1ck-guo committed 175 days ago

Verified 92d31fa2

Fix torch_zp infer bug & API disable_deterministic_algorithms bug (#733)

WeiweiZhang1 committed 175 days ago

Verified 71dab1dc

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 175 days ago

c772a7a3

update nvfp & mxfp quant, add llmcompressor nv_fp/mx_fp format export

WeiweiZhang1 committed 175 days ago

732c35f5

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 176 days ago

4cd5acf2

Merge branch 'main' into enable_mxfp_exporting

WeiweiZhang1 committed 176 days ago

Verified 1a3bd5ac

fix bug for exporting afp8 fake format (#731)

n1ck-guo committed 176 days ago

Verified 978cac11

add original convert file and support for the newest llama.cpp (#729)

n1ck-guo committed 177 days ago

Verified 2acf7864

make the tuning deterministic and move infrequently used arguments to kwargs (#726)

wenhuach21 committed 178 days ago

Verified 478aedbf

new cast_to_nvfp4 with high performance (#727)

xin3he committed 178 days ago

Verified de2b48a6

update gguf convert.py and support for gpt-oss (#721)

n1ck-guo committed 180 days ago

Verified 73ecd7f8

fix fp8 model input issue (#724)

wenhuach21 committed 181 days ago

Verified 9113fa8e

Fix hpu CI (#723)

XuehaoSun committed 181 days ago

Verified 173b0921

update autoround mllm and support Mistral 3.2 series (#713)

n1ck-guo committed 181 days ago

Verified 2e911b76

Freeze torchvision version in CI (#720)

XuehaoSun committed 182 days ago

Verified 4b9fbed3

Bump transformers in /test/test_cuda (#719)

dependabot[bot] committed 182 days ago

Verified 80a09172

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 182 days ago

0beaf1c6

Older