intel/auto-round

Pull Requests Commits

add compress_layer_names utility to reduce log verbosity for unquantized layers

xin3he committed 35 days ago

ce6374e4

add support for w4a16_mixed (#1326)

n1ck-guo committed 36 days ago

Verified 7cff6af5

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

n1ck-guo committed 36 days ago

Verified eb2ccdc3

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

wenhuach21 committed 36 days ago

Verified 0c0a0c1d

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

wenhuach21 committed 36 days ago

Verified 6bc1d344

fix bug of exporting fp8 static (#1361)

n1ck-guo committed 36 days ago

Verified b04f69c4

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

scopophobic committed 37 days ago

Verified eaabde4a

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

n1ck-guo committed 37 days ago

Verified 528c9c82

Autoround in vLLM Office Hours (#1322)

yiliu30 committed 37 days ago

Verified b3f6f1fb

Fix cpu ut for transformers v5 (#1333)

Kaihui-intel committed 37 days ago

Verified f6e7e303

Fix CPU CI (#1344)

XuehaoSun committed 38 days ago

Verified 8eec5d8a

add copilot-instructions (#1341)

xin3he committed 38 days ago

Verified 0fe5c0a7

refactor eval and add UT (#1324)

xin3he committed 39 days ago

Verified 14eacb1f

Add Chinese README (#1335)

ZaneMark committed 39 days ago

Verified 71b385d2

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

wenhuach21 committed 39 days ago

Verified ca133621

Fix attribute bug for diffusion model (#1338)

mengniwang95 committed 39 days ago

Verified a4ee3a00

update release package and bump version (#1327)

chensuyue committed 40 days ago

Verified 00702194

format add check for scheme args (#1332)

n1ck-guo committed 40 days ago

Verified 7f1dee6e

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

yiliu30 committed 40 days ago

Verified d9d20a12

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

SwekeR-463 committed 41 days ago

Verified 6190869b

fix tied weights keys bug (#1330)

wenhuach21 committed 42 days ago

Verified 25364d21

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

xin3he committed 42 days ago

Verified 46224d4a

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

n1ck-guo committed 42 days ago

Verified 24e43976

simplify pull_request_template.md (#1328)

xin3he committed 42 days ago

Verified cf37d8e6

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

wenhuach21 committed 43 days ago

Verified 57d1a8ac

set predefined ignore layers (#1318)

wenhuach21 committed 43 days ago

Verified 7c397e14

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

wenhuach21 committed 43 days ago

Verified f654e52d

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

Copilot committed 44 days ago

Verified eaf5885a

fix XPU CI hang issue (#1261)

xin3he committed 44 days ago

Verified 57af5b7f

fix bug of format (#1287)

n1ck-guo committed 44 days ago

Verified 5ba31b6c

Older