intel/auto-round

Pull Requests Commits

n1ck-guo committed 1 day ago

ab48faf8

fix cuda ut fail

n1ck-guo committed 1 day ago

afe2166c

add support for w4a16_mixed (#1326)

n1ck-guo committed 2 days ago

Verified 7cff6af5

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

n1ck-guo committed 2 days ago

Verified eb2ccdc3

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

wenhuach21 committed 2 days ago

Verified 0c0a0c1d

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

wenhuach21 committed 2 days ago

Verified 6bc1d344

fix bug of exporting fp8 static (#1361)

n1ck-guo committed 2 days ago

Verified b04f69c4

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

scopophobic committed 3 days ago

Verified eaabde4a

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

n1ck-guo committed 3 days ago

Verified 528c9c82

Autoround in vLLM Office Hours (#1322)

yiliu30 committed 3 days ago

Verified b3f6f1fb

Fix cpu ut for transformers v5 (#1333)

Kaihui-intel committed 3 days ago

Verified f6e7e303

Fix CPU CI (#1344)

XuehaoSun committed 4 days ago

Verified 8eec5d8a

add copilot-instructions (#1341)

xin3he committed 4 days ago

Verified 0fe5c0a7

refactor eval and add UT (#1324)

xin3he committed 5 days ago

Verified 14eacb1f

Add Chinese README (#1335)

ZaneMark committed 5 days ago

Verified 71b385d2

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

wenhuach21 committed 5 days ago

Verified ca133621

Fix attribute bug for diffusion model (#1338)

mengniwang95 committed 5 days ago

Verified a4ee3a00

update release package and bump version (#1327)

chensuyue committed 6 days ago

Verified 00702194

format add check for scheme args (#1332)

n1ck-guo committed 6 days ago

Verified 7f1dee6e

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

yiliu30 committed 6 days ago

Verified d9d20a12

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

SwekeR-463 committed 7 days ago

Verified 6190869b

fix tied weights keys bug (#1330)

wenhuach21 committed 8 days ago

Verified 25364d21

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

xin3he committed 8 days ago

Verified 46224d4a

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

n1ck-guo committed 8 days ago

Verified 24e43976

simplify pull_request_template.md (#1328)

xin3he committed 8 days ago

Verified cf37d8e6

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

wenhuach21 committed 9 days ago

Verified 57d1a8ac

set predefined ignore layers (#1318)

wenhuach21 committed 9 days ago

Verified 7c397e14

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

wenhuach21 committed 9 days ago

Verified f654e52d

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

Copilot committed 9 days ago

Verified eaf5885a

fix XPU CI hang issue (#1261)

xin3he committed 10 days ago

Verified 57af5b7f

Older