intel/auto-round

Pull Requests Commits

fix bug of gguf and support for LiquidAI/LFM2-1.2B (#927)

n1ck-guo committed 137 days ago

Verified 80c8de57

optimize rtn for int woq (#924)

wenhuach21 committed 137 days ago

Verified da55e27a

Fix act config exporting for mixed schemes (#903)

WeiweiZhang1 committed 138 days ago

Verified 5bb16b05

Extend mxfp loading dtypes (#916)

yiliu30 committed 138 days ago

Verified 0164077e

Loosen the packing restrictions for mxfp&nvfp (#911)

WeiweiZhang1 committed 138 days ago

Verified dcfacefa

add numba for cpu lib (#919)

yiliu30 committed 138 days ago

Verified 41986b54

fix llama 4 ut (#896)

n1ck-guo committed 138 days ago

Verified b738ea0a

support disable_opt_rtn in auto-scheme (#913)

wenhuach21 committed 138 days ago

Verified 5de9fbc5

Revert "Extend mxfp loading dtypes (#907)" (#915)

wenhuach21 committed 139 days ago

Verified 46812de0

fix torch compile issue in AutoScheme (#909)

wenhuach21 committed 142 days ago

Verified 1d912079

block dataset logger info (#908)

n1ck-guo committed 142 days ago

Verified fe622130

Extend mxfp loading dtypes (#907)

yiliu30 committed 142 days ago

Verified 0c2619cf

remove numba from requirments (#905)

yiliu30 committed 142 days ago

Verified 56f469e4

try to fix gguf issue (#886)

wenhuach21 committed 142 days ago

Verified 6c8974bd

support automatic mixed bits assignment (#851)

wenhuach21 committed 142 days ago

Verified 0f64ed0c

fix nvfp act quantization bug (#891)

WeiweiZhang1 committed 143 days ago

Verified fbc41c8d

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

xin3he committed 143 days ago

Verified 9d62109d

better help printing information (#883)

n1ck-guo committed 144 days ago

Verified 1b804bef

Add GPT-OSS quant support (#887)

yiliu30 committed 144 days ago

Verified 081c92a5

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

xin3he committed 144 days ago

Verified db560e04

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

chensuyue committed 145 days ago

Verified d7d2a405

fix vlm gguf ut (#895)

n1ck-guo committed 145 days ago

Verified 65b7ec2f

Fix rtn tuning_device issue (#893)

Kaihui-intel committed 145 days ago

Verified 7beac1b6

update require accelerate version (#888)

n1ck-guo committed 146 days ago

Verified 747b7af3

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

pre-commit-ci[bot] committed 146 days ago

Verified f2b9aefc

restrict accelerate version (#885)

wenhuach21 committed 146 days ago

Verified d0589129

Fix act calibration bug (#880)

mengniwang95 committed 147 days ago

Verified b693a2a6

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

xin3he committed 148 days ago

Verified 233a6c8f

fp8 exporting bugfix (#874)

WeiweiZhang1 committed 148 days ago

Verified f56804a1

Support Flux quantization (#850)

mengniwang95 committed 148 days ago

Verified 752b2f2a

Newer Older