intel/auto-round

Pull Requests Commits

revert two changes to reduce risk

wenhuach21 committed 50 days ago

b9c27bdd

wenhuach21 committed 50 days ago

ce5bc1be

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

wenhuach21 committed 50 days ago

af015b0f

fix some issue, remove one clear memory, add packing, 13.5m

wenhuach21 committed 50 days ago

9442ebb9

remove packing to 14.5 mins

wenhuach21 committed 51 days ago

0fa6499e

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

pre-commit-ci[bot] committed 51 days ago

8fd55be8

this improve the speed from 16m+ to 15m with torch compile

wenhuach21 committed 51 days ago

b44b71cd

cli support for positional arguments model (#979)

n1ck-guo committed 52 days ago

Verified b9245b58

refine readme (#978)

wenhuach21 committed 52 days ago

Verified 3f7bdace

enhance auto device map and support XPU (#961)

xin3he committed 54 days ago

Verified 06dd686a

disable compile packing by default (#975)

yiliu30 committed 54 days ago

Verified 8c767db6

fix cuda CI backend issue, fixtypo (#974)

WeiweiZhang1 committed 54 days ago

Verified 635eded9

merge main branch to alg_ext (#970)

wenhuach21 committed 55 days ago

Verified 9ecfaa5d

support for model scope (#957)

n1ck-guo committed 55 days ago

Verified 2448dcf2

clean code (#968)

wenhuach21 committed 55 days ago

Verified 3c1a6781

enhance flux doc (#967)

mengniwang95 committed 56 days ago

Verified 7635f7ea

fix rtn bug (#966)

mengniwang95 committed 56 days ago

Verified c4ef9a82

fix bug of imatrix contains 0 (#955)

n1ck-guo committed 56 days ago

Verified 5e33cbce

[1/N] Initial vllm-ext evaluation support (MXFP4 MOE) (#935)

yiliu30 committed 56 days ago

Verified e8bc3536

fix critic disable_opt_rtn regression (#963)

wenhuach21 committed 56 days ago

Verified 282aab66

update readme (#962)

wenhuach21 committed 56 days ago

Verified 7d8016d9

refine AutoScheme readme/code (#958)

wenhuach21 committed 56 days ago

Verified 8ac82a4a

add logo (#960)

wenhuach21 committed 57 days ago

Verified eb2facd9

add self attribution and fix avg_bits error (#956)

xin3he committed 57 days ago

Verified 12c49846

Reduce AutoSchem VRAM usage by up to 10X (#944)

wenhuach21 committed 57 days ago

Verified 90c2fb4c

update gguf and support for CompressedLinear (#950)

n1ck-guo committed 58 days ago

Verified fbb9c13b

update readme for sglang support (#953)

WeiweiZhang1 committed 58 days ago

Verified 824a21fb

refactor utils file (#943)

n1ck-guo committed 58 days ago

Verified f1b5c72b

update readme (#949)

wenhuach21 committed 58 days ago

Verified 959ac67c

Add diffusion README (#923)

mengniwang95 committed 59 days ago

Verified 97512a46

Older