Skip to content

[OMNIML-6180] Let the T5 and Mixtral hf_ptq tests share the GPU #2926

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
shengliangxu merged 1 commit into from
Oct 22, 2026
Merged

[OMNIML-6180] Let the T5 and Mixtral hf_ptq tests share the GPU #2926

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
20 changes: 12 additions & 8 deletions tests/examples/hf_ptq/test_llm_ptq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,11 +19,18 @@
from _test_utils.examples.models import MIXTRAL_PATH, T5_PATH, TINY_LLAMA_PATH


def _run_sharing_the_gpu(command: PTQCommand, model_path: str):
# Sharing the GPU, so set a batch size: hf_ptq sizes one to fill the free GPU memory.
if command.calib_batch_size is None:
command = dataclasses.replace(command, calib_batch_size=command.calib)
command.run(model_path)


# Encoder-decoder representative; BART shares the same export path.
@pytest.mark.parametrize("command", [PTQCommand(quant="fp8", min_sm=89)], ids=PTQCommand.param_str)
@pytest.mark.usefixtures("exclusive_gpu")
@pytest.mark.usefixtures("shared_gpu")
def test_ptq_t5(command):
command.run(T5_PATH)
_run_sharing_the_gpu(command, T5_PATH)


@pytest.mark.parametrize(
Expand All @@ -33,9 +40,9 @@ def test_ptq_t5(command):
],
ids=PTQCommand.param_str,
)
@pytest.mark.usefixtures("exclusive_gpu")
@pytest.mark.usefixtures("shared_gpu")
def test_ptq_mixtral(command):
command.run(MIXTRAL_PATH)
_run_sharing_the_gpu(command, MIXTRAL_PATH)


# Per-format export on tiny models (int8_weight_only, nvfp4_awq_lite, ...) is covered by
Expand Down Expand Up @@ -77,7 +84,4 @@ def test_ptq_mixtral(command):
)
@pytest.mark.usefixtures("shared_gpu")
def test_ptq_llama(command):
# Sharing the GPU, so set a batch size: hf_ptq sizes one to fill the free GPU memory.
if command.calib_batch_size is None:
command = dataclasses.replace(command, calib_batch_size=command.calib)
command.run(TINY_LLAMA_PATH)
_run_sharing_the_gpu(command, TINY_LLAMA_PATH)
Loading