Skip to content

[Tests] Start oneshot tests on CPU #1555

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
dsikka merged 2 commits into from
Jun 25, 2025
Merged

[Tests] Start oneshot tests on CPU #1555

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8d575e2
remove device map deployment from tests
kylesayrs Jun 20, 2025
4de9eea
Merge branch 'main' into kylesayrs/testing-device-map
dsikka Jun 25, 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
1 change: 0 additions & 1 deletion tests/llmcompressor/recipe/test_recipe_parsing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,6 @@ def setup_model_and_config(tmp_path):
"""
model = AutoModelForCausalLM.from_pretrained(
"Xenova/llama2.c-stories110M",
device_map="auto",
torch_dtype="auto",
)

Expand Down
10 changes: 3 additions & 7 deletions tests/llmcompressor/transformers/finetune/test_oneshot_then_finetune.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ def setUp(self):
def test_oneshot_sparsification_then_finetune(self):
recipe_str = "tests/llmcompressor/transformers/obcq/recipes/test_tiny2.yaml"
model = AutoModelForCausalLM.from_pretrained(
"nm-testing/llama2.c-stories15M", device_map="auto", torch_dtype="auto"
"nm-testing/llama2.c-stories15M", torch_dtype="auto"
)
dataset = "open_platypus"
concatenate_data = False
Expand All @@ -47,12 +47,11 @@ def test_oneshot_sparsification_then_finetune(self):
# Explictly decompress the model for training using quantization_config
model = AutoModelForCausalLM.from_pretrained(
self.output / "oneshot_out",
device_map="auto",
torch_dtype="auto",
quantization_config=self.quantization_config,
)
distill_teacher = AutoModelForCausalLM.from_pretrained(
"nm-testing/llama2.c-stories15M", device_map="auto", torch_dtype="auto"
"nm-testing/llama2.c-stories15M", torch_dtype="auto"
)
dataset = "open_platypus"
concatenate_data = False
Expand Down Expand Up @@ -88,7 +87,6 @@ def test_oneshot_sparsification_then_finetune(self):
# Explictly decompress the model for training using quantization_config
model = AutoModelForCausalLM.from_pretrained(
output_dir,
device_map="auto",
torch_dtype="auto",
quantization_config=self.quantization_config,
)
Expand All @@ -112,7 +110,7 @@ def test_oneshot_quantization_then_finetune(self):
)

model = AutoModelForCausalLM.from_pretrained(
"TinyLlama/TinyLlama-1.1B-Chat-v1.0", device_map="auto", torch_dtype="auto"
"TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype="auto"
)
dataset = "open_platypus"
concatenate_data = False
Expand All @@ -136,7 +134,6 @@ def test_oneshot_quantization_then_finetune(self):
quantization_config = CompressedTensorsConfig(run_compressed=False)
model = AutoModelForCausalLM.from_pretrained(
output_dir,
device_map="auto",
torch_dtype="auto",
quantization_config=quantization_config,
)
Expand All @@ -159,7 +156,6 @@ def test_oneshot_quantization_then_finetune(self):
# test reloading checkpoint and final model
model = AutoModelForCausalLM.from_pretrained(
output_dir,
device_map="auto",
torch_dtype="auto",
quantization_config=quantization_config,
)
Expand Down
2 changes: 0 additions & 2 deletions tests/llmcompressor/transformers/obcq/test_consecutive_runs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,6 @@ def _test_consecutive_runs(

first_model = AutoModelForCausalLM.from_pretrained(
self.output_first,
device_map="auto",
torch_dtype="auto",
quantization_config=self.quantization_config,
)
Expand Down Expand Up @@ -74,7 +73,6 @@ def _test_consecutive_runs(
second_model = AutoModelForCausalLM.from_pretrained(
self.output_second,
quantization_config=self.quantization_config,
device_map="auto",
torch_dtype="auto",
)

Expand Down