-
Notifications
You must be signed in to change notification settings - Fork 351
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
TRT-10 GA Support for main branch #2781
Conversation
37d1674
to
ad9896a
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
- Can you add tensorrt==10.0.1.6 in our py/requirements.txt ? (https://github.com/pytorch/TensorRT/blob/trt_10_ga_cloned_from_main/py/requirements.txt)
- Also update trt version in dev_dep_versions.yml (https://github.com/pytorch/TensorRT/blob/trt_10_ga_cloned_from_main/dev_dep_versions.yml)
c7a5a3b
to
3866636
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Changes LGTM. pending rebase
3866636
to
0e6aada
Compare
5079c1c
to
20b34e2
Compare
Line 45 in 20b34e2
|
@HolyWu Made the changes. Thanks for the review! |
fd77a55
to
35461e1
Compare
35461e1
to
1dc194a
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There are some changes that do not conform to Python style guidelines:
--- /home/runner/work/TensorRT/TensorRT/tests/py/dynamo/models/test_dyn_models.py 2024-04-29 19:55:18.604129+00:00
+++ /home/runner/work/TensorRT/TensorRT/tests/py/dynamo/models/test_dyn_models.py 2024-04-29 19:57:14.310783+00:00
@@ -7,13 +7,11 @@
from torch_tensorrt.dynamo.utils import COSINE_THRESHOLD, cosine_similarity
assertions = unittest.TestCase()
-@unittest.skip(
- "Skipping this test for now due to a bug"
-)
+@unittest.skip("Skipping this test for now due to a bug")
@pytest.mark.unit
def test_base_dynamic(ir):
"""
Tests the model (which is fully convertible) with dynamic shapes
"""
@@ -67,13 +65,11 @@
with torch.no_grad():
torch.cuda.empty_cache()
-@unittest.skip(
- "Skipping this test for now due to a bug"
-)
+@unittest.skip("Skipping this test for now due to a bug")
@pytest.mark.unit
def test_base_dynamic_fallback(ir):
"""
Tests the model with dynamic shapes where torch.abs op is forced to run in PyTorch
"""
f8acc75
to
a777795
Compare
Description
This PR runs CI to test TRT-10 GA support for main branch.