Skip to content

disable itrex format first #998

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

disable itrex format first #998

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
7d34e57
disable itrex format first
WeiweiZhang1 Nov 6, 2025
8dc5c90
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Nov 6, 2025
cc13a65
revert typo
WeiweiZhang1 Nov 11, 2025
d41eac3
revert typo
WeiweiZhang1 Nov 11, 2025
528bcba
Merge branch 'main' into disable_itrex_format_first
WeiweiZhang1 Nov 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 0 additions & 2 deletions auto_round/utils/common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,8 +88,6 @@ def __init__(self):
"auto_round:gptqmodel",
"auto_round:auto_awq",
"auto_round:llm_compressor",
"itrex",
"itrex_xpu",
"fake",
"llm_compressor",
)
Expand Down
22 changes: 0 additions & 22 deletions test/test_cpu/test_autoround.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -162,28 +162,6 @@ def test_nv_fp4(self):
print(result["results"]["lambada_openai"]["acc,none"])
self.assertGreater(result["results"]["lambada_openai"]["acc,none"], 0.35)

def test_default(self):
bits, group_size, sym = 4, 128, False
autoround = AutoRound(
self.model,
self.tokenizer,
bits=bits,
group_size=group_size,
sym=sym,
iters=2,
seqlen=2,
dataset=self.llm_dataloader,
)
autoround.quantize()

autoround.save_quantized(output_dir="./saved", inplace=False, format="itrex")
try:
import auto_gptq
except:
return
if torch.cuda.is_available():
autoround.save_quantized(output_dir="./saved", inplace=False)

def test_w4g1(self):
model_name = "/tf_dataset/auto_round/models/facebook/opt-125m"
bits, group_size, sym = 4, -1, True
Expand Down
1 change: 0 additions & 1 deletion test/test_cpu/test_autoround_acc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,6 @@
from transformers import AutoModelForCausalLM, AutoTokenizer

from auto_round import AutoRound # pylint: disable=E0401
from auto_round.export.export_to_itrex.export import pack_model # pylint: disable=E0401


class LLMDataLoader:
Expand Down