Skip to content

update bits in UT #986

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

Merged
merged 1 commit into from
Nov 4, 2025
Merged

update bits in UT #986

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 4 additions & 4 deletions test/test_cuda/test_auto_scheme.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,7 @@ def test_shared_layers(self):
@multi_card
def test_multi_card(self):
model_name = "/models/Qwen3-0.6B"
target_bits = 5.265
target_bits = 4.5
for device_map in ["auto", "0,1", "0", None]:
scheme = AutoScheme(avg_bits=target_bits, options=("NVFP4"))
ar = AutoRound(model=model_name, scheme=scheme, iters=0, nsamples=1, device_map=device_map)
Expand All @@ -96,7 +96,7 @@ def test_multi_card(self):
@multi_card
def test_multi_card_1(self):
model_name = "/models/Qwen3-0.6B"
target_bits = 5.265
target_bits = 4.5
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(model_name)
Expand All @@ -110,7 +110,7 @@ def test_multi_card_1(self):

def test_non_low_gpu_mem_usage(self):
model_name = "/models/Qwen3-0.6B"
target_bits = 5.265
target_bits = 4.5
# for device_map in ["auto", "0,1", "0", None]:
scheme = AutoScheme(avg_bits=target_bits, options=("NVFP4"), low_gpu_mem_usage=False, device_map="auto")

Expand All @@ -123,7 +123,7 @@ def test_non_low_gpu_mem_usage(self):
@multi_card
def test_dict_device_map(self):
model_name = "/models/Qwen3-8B"
target_bits = 8.755
target_bits = 8.25
device_map = {"up_proj": 0, "down_proj": 1}

scheme = AutoScheme(avg_bits=target_bits, options=("MXFP8"))
Expand Down