intel/auto-round

Pull Requests Commits

set predefined ignore layers (#1318)

wenhuach21 committed 107 days ago

c0e08de2

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

Copilot committed 107 days ago

d5395565

fix XPU CI hang issue (#1261)

xin3he committed 107 days ago

72b8801d

fix bug of format (#1287)

n1ck-guo committed 107 days ago

442edd6c

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

mengniwang95 committed 107 days ago

2a50fea8

open source delta loss (#1300)

wenhuach21 committed 107 days ago

4c28001a

fix ignore layers regression (#1302)

wenhuach21 committed 107 days ago

e736cfec

Remove itrex format (#1301)

Kaihui-intel committed 107 days ago

5b1f5f17

Extensible Module Weight Type Conversion Framework. (#1375)

xin3he committed 107 days ago

Verified 53f20cf1

Fix FP8 MLA (#1343)

yiliu30 committed 107 days ago

Verified db77f3b7

feat: handle per-tensor FP8 dequantization for Devstral models (#1356)

SwekeR-463 committed 108 days ago

Verified eddb6de2

fix copy python file issue (#1372)

wenhuach21 committed 110 days ago

Verified 29956d91

add support for w4a16_mixed (#1326)

n1ck-guo committed 110 days ago

Verified 7cff6af5

fix cuda ut fail for transformers v5.0 (#1357)

n1ck-guo committed 110 days ago

Verified eb2ccdc3

support qwen3-next/glm4-moe/deepseekv3 monkey patch for transformers 5 (#1367)

wenhuach21 committed 110 days ago

Verified 0c0a0c1d

support qwen3-moe/glm-4.7-flash monkey patch for transformers 5 (#1354)

wenhuach21 committed 111 days ago

Verified 6bc1d344

fix bug of exporting fp8 static (#1361)

n1ck-guo committed 111 days ago

Verified b04f69c4

Refactor FP8 dequantization and detection using registry pattern (#1348)

scopophobic committed 111 days ago

Verified eaabde4a

refactor auto_round api, using local symbol table to pass all args (#1358)

n1ck-guo committed 111 days ago

Verified 528c9c82

Autoround in vLLM Office Hours (#1322)

yiliu30 committed 112 days ago

Verified b3f6f1fb

Fix cpu ut for transformers v5 (#1333)

Kaihui-intel committed 112 days ago

Verified f6e7e303

Fix CPU CI (#1344)

XuehaoSun committed 112 days ago

Verified 8eec5d8a

add copilot-instructions (#1341)

xin3he committed 113 days ago

Verified 0fe5c0a7

Optimize CPU RAM peak memeory during quantization

lvliang-intel committed 113 days ago

74bdadc1

refactor eval and add UT (#1324)

xin3he committed 114 days ago

Verified 14eacb1f

Add Chinese README (#1335)

ZaneMark committed 114 days ago

Verified 71b385d2

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

wenhuach21 committed 114 days ago

Verified ca133621

Fix attribute bug for diffusion model (#1338)

mengniwang95 committed 114 days ago

Verified a4ee3a00

update release package and bump version (#1327)

chensuyue committed 114 days ago

Verified 00702194

format add check for scheme args (#1332)

n1ck-guo committed 114 days ago

Verified 7f1dee6e

Newer Older