intel/auto-round

Pull Requests Commits

chensuyue committed 18 days ago

89c0d813

Merge branch 'main' into suyue/ci

chensuyue committed 18 days ago

Verified 893cb657

Grep core dumped issue in UT test (#1484)

chensuyue committed 18 days ago

Verified c2152e48

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

pre-commit-ci[bot] committed 19 days ago

234955cc

chensuyue committed 19 days ago

5becea12

add cuda llmc test back

chensuyue committed 19 days ago

f805e199

add qwen35 ut (#1482)

wenhuach21 committed 19 days ago

Verified 2b5d1175

update test requirements for xpu

chensuyue committed 19 days ago

9119bcba

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

pre-commit-ci[bot] committed 19 days ago

a9701414

enhance llmc CI on GPU and XPU

chensuyue committed 19 days ago

c8467ff1

support qwen3_5 moe (#1476)

wenhuach21 committed 20 days ago

Verified 1b37c316

Fix typo: remove extra backtick in comment (#1481)

04cb committed 20 days ago

Verified 34acefd5

Fix HPU CI: apply temporary version restriction on compressed_tensors (#1479)

XuehaoSun committed 21 days ago

Verified 81d27d2b

Add envs.py for environment checks and update imports in test files (#1432)

xin3he committed 22 days ago

Verified 388e6c0b

reduce AutoGPTQ priority and add transformer requirement (#1467)

xin3he committed 22 days ago

Verified e7e1c78d

fix: qwen3-next NVFP4 quantization returns act_max incorrectly (#1470)

xin3he committed 22 days ago

Verified 229d1fef

Fix cuda ut workflow (#1472)

XuehaoSun committed 22 days ago

Verified b55ffb90

support glm5 (#1466)

wenhuach21 committed 23 days ago

Verified 62c9808d

Fix KeyError when GPU is missing from accelerate max_memory (#1457)

lvliang-intel committed 24 days ago

Verified b697e1d2

support multiple device evaluation for activation quantized model (#1394)

wenhuach21 committed 25 days ago

Verified bd4241df

Update compatibility test and version to 0.10.2 (#1463)

XuehaoSun committed 25 days ago

Verified 23c16c6c

Support load FP8 model on HPU (#1449)

yiliu30 committed 25 days ago

Verified aef6d3c4

fix: preserve classmethod descriptor in from_pretrained monkey patch (#1460)

yiliu30 committed 25 days ago

Verified 0d0f8367

Fix requirements packaging for source distribution (#1455)

timkpaine committed 36 days ago

Verified c0dc55fc

[Regression] fix FP8_STATIC loading (#1452)

xin3he committed 37 days ago

Verified 9855b4ba

Attach `act_max_hook` for FP8 model (#1447)

yiliu30 committed 37 days ago

Verified 81c8ee42

bump version (#1445)

chensuyue committed 37 days ago

Verified 0f087c91

fix bug of evaluate_accuracy (#1430)

xin3he committed 38 days ago

Verified 40253afe

update readme for Intel xpu usage (#1441)

chensuyue committed 38 days ago

Verified f16d57d7

update logic for compatibility with gptqmodel:exllamav2 backend (#1438)

xin3he committed 38 days ago

Verified 86231c44

Older