Skip to content
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.

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

fix OVModelForCausalLM for auto device #433

Merged
merged 1 commit into from
Sep 21, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
3 changes: 2 additions & 1 deletion optimum/intel/openvino/modeling_decoder.py
Original file line number Diff line number Diff line change
Expand Up @@ -154,7 +154,8 @@ def update_pkv_precision(self, force_fp32=False):
pkv_precision = Type.f32
if not force_fp32:
device = self._device.upper()
pkv_precision = core.get_property(device, "INFERENCE_PRECISION_HINT")
if "INFERENCE_PRECISION_HINT" in core.get_property(device, "SUPPORTED_PROPERTIES"):
pkv_precision = core.get_property(device, "INFERENCE_PRECISION_HINT")
# ov_config["INFERENCE_PRECISION_HINT"] may override the prefer precision
if self.ov_config:
inference_precision_hint = self.ov_config.get("INFERENCE_PRECISION_HINT", "")
Expand Down
8 changes: 8 additions & 0 deletions tests/openvino/test_modeling.py
Original file line number Diff line number Diff line change
Expand Up @@ -558,6 +558,14 @@ def test_compare_with_and_without_past_key_values(self):
del model_without_pkv
gc.collect()

def test_auto_device_loading(self):
model_id = MODEL_NAMES["gpt2"]
model = OVModelForCausalLM.from_pretrained(model_id, export=True, use_cache=True, device="AUTO")
model.half()
self.assertEqual(model._device, "AUTO")
del model
gc.collect()


class OVModelForMaskedLMIntegrationTest(unittest.TestCase):
SUPPORTED_ARCHITECTURES = (
Expand Down