intel/auto-round

Pull Requests Commits

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

pre-commit-ci[bot] committed 125 days ago

2377e150

Merge branch 'main' into Chinesization

ZaneMark committed 125 days ago

Verified c7402dd4

Autoround in vLLM Office Hours (#1322)

yiliu30 committed 126 days ago

Verified b3f6f1fb

Fix cpu ut for transformers v5 (#1333)

Kaihui-intel committed 126 days ago

Verified f6e7e303

Fix CPU CI (#1344)

XuehaoSun committed 126 days ago

Verified 8eec5d8a

add copilot-instructions (#1341)

xin3he committed 127 days ago

Verified 0fe5c0a7

Update step_by_step_CN.md

ZaneMark committed 127 days ago

Verified 1ffcd326

Update step_by_step_CN.md

ZaneMark committed 127 days ago

Verified 478a2ac4

Update step_by_step.md

ZaneMark committed 127 days ago

Verified df1d0041

add jump links for all docs

ZaneMark committed 127 days ago

8cfe370b

refactor eval and add UT (#1324)

xin3he committed 128 days ago

Verified 14eacb1f

Add Chinese README (#1335)

ZaneMark committed 128 days ago

Verified 71b385d2

Fix issue where predefined ignore layers incorrectly apply to GGUF (#1340)

wenhuach21 committed 128 days ago

Verified ca133621

Fix attribute bug for diffusion model (#1338)

mengniwang95 committed 128 days ago

Verified a4ee3a00

update release package and bump version (#1327)

chensuyue committed 128 days ago

Verified 00702194

format add check for scheme args (#1332)

n1ck-guo committed 128 days ago

Verified 7f1dee6e

Delay materializing the replaced model weights until quantization (#1307)

yiliu30 committed 128 days ago

Verified d9d20a12

(feat): add support for g2 fp8 on cpu with LUT (#1254)

SwekeR-463 committed 130 days ago

Verified 6190869b

fix tied weights keys bug (#1330)

wenhuach21 committed 131 days ago

Verified 25364d21

Update publication dates in README and add recipe configuration detai… (#1329)

xin3he committed 131 days ago

Verified 46224d4a

[GGUF] using quant_nontext_module to control whether quant vision model (#1317)

n1ck-guo committed 131 days ago

Verified 24e43976

simplify pull_request_template.md (#1328)

xin3he committed 131 days ago

Verified cf37d8e6

add blockwise way in pure rtn to ease module replacements (#1320)

wenhuach21 committed 132 days ago

Verified 57d1a8ac

set predefined ignore layers (#1318)

wenhuach21 committed 132 days ago

Verified 7c397e14

fix low_cpu and set it to True as default (#1288)

wenhuach21 committed 132 days ago

Verified f654e52d

Add issue templates and PR template with required fields (#1309)

Copilot committed 132 days ago

Verified eaf5885a

fix XPU CI hang issue (#1261)

xin3he committed 132 days ago

Verified 57af5b7f

fix bug of format (#1287)

n1ck-guo committed 133 days ago

Verified 5ba31b6c

Enable q_scale calibration for deepseek v2 on Gaudi (#1299)

mengniwang95 committed 133 days ago

Verified d8ed35a8

open source delta loss (#1300)

wenhuach21 committed 134 days ago

Verified 587eadb8

Older