intel/auto-round

Pull Requests Commits

update build from source version control

chensuyue committed 69 days ago

b63c44bb

remove numba from requirments (#905)

yiliu30 committed 69 days ago

Verified 56f469e4

try to fix gguf issue (#886)

wenhuach21 committed 70 days ago

Verified 6c8974bd

support automatic mixed bits assignment (#851)

wenhuach21 committed 70 days ago

Verified 0f64ed0c

fix nvfp act quantization bug (#891)

WeiweiZhang1 committed 70 days ago

Verified fbc41c8d

speedup quant and evaluation, fix recompile issue (#897)

xin3he committed 70 days ago

Verified 9d62109d

better help printing information (#883)

n1ck-guo committed 71 days ago

Verified 1b804bef

Add GPT-OSS quant support (#887)

yiliu30 committed 71 days ago

Verified 081c92a5

move ste from quant to round for nvfp4 (#889)

xin3he committed 71 days ago

Verified db560e04

update alg_ext.abi3.so with python compatible version (#894)

chensuyue committed 72 days ago

Verified d7d2a405

fix vlm gguf ut (#895)

n1ck-guo committed 72 days ago

Verified 65b7ec2f

Fix rtn tuning_device issue (#893)

Kaihui-intel committed 72 days ago

Verified 7beac1b6

update require accelerate version (#888)

n1ck-guo committed 73 days ago

Verified 747b7af3

[pre-commit.ci] pre-commit autoupdate (#868)

pre-commit-ci[bot] committed 73 days ago

Verified f2b9aefc

restrict accelerate version (#885)

wenhuach21 committed 73 days ago

Verified d0589129

Fix act calibration bug (#880)

mengniwang95 committed 75 days ago

Verified b693a2a6

stop try except and add back missing arguments (#884)

xin3he committed 75 days ago

Verified 233a6c8f

fp8 exporting bugfix (#874)

WeiweiZhang1 committed 75 days ago

Verified f56804a1

Support Flux quantization (#850)

mengniwang95 committed 75 days ago

Verified 752b2f2a

Fix Cuda CI failures due to Transformers and AWQ incompatibility (#882)

WeiweiZhang1 committed 76 days ago

Verified 7e433854

Optimize CPU unit test workflow (#881)

XuehaoSun committed 76 days ago

Verified 6e567b72

fix vllm backend evaluation (#872)

xin3he committed 77 days ago

Verified 5e22944a

fix device bug (#873)

xin3he committed 77 days ago

Verified eb5cdcd8

fix seqlen bug and calib slow of mllm tuning (#871)

n1ck-guo committed 77 days ago

Verified 72107919

fix FP8 model as input and backend issue (#864)

wenhuach21 committed 86 days ago

Verified 7b8e280f

raise vlm loading error (#863)

wenhuach21 committed 86 days ago

Verified ab94a4b3

fix bug of get_layer_names_in_block (#861)

wenhuach21 committed 86 days ago

Verified 25d3044c

fix save_quantied format cheaker (#857)

WeiweiZhang1 committed 88 days ago

Verified 780091dc

fix bug of data_type fp8_sym (#855)

n1ck-guo committed 90 days ago

Verified ba42398f

Refine `BackendInfo` to include act fields (#848)

yiliu30 committed 90 days ago

Verified 27074ba9

Older