Comments (2)
Notably, the below code works:
import torch
import torch_tensorrt
class Model(torch.nn.Module):
def __init__(self):
super().__init__()
def forward(self, topk_ind):
gather_index = topk_ind.unsqueeze(-1)
return gather_index
def main():
model = Model().cuda()
model.eval()
topk_ind = torch.randint(8400, size=(1, 300)).cuda()
inputs = [
torch_tensorrt.Input(topk_ind.shape, dtype=torch.int32),
]
enabled_precisions = {torch.half, torch.float32}
trt_model = torch_tensorrt.compile(
model,
inputs=inputs,
enabled_precisions=enabled_precisions,
truncate_long_and_double=True,
min_block_size=1,
)
if __name__ == "__main__":
main()
which suggests it's not the unsqueeze
causing problems. The original code I was testing that raised the error was:
import torch
import torch_tensorrt
class Model(torch.nn.Module):
def __init__(self):
super().__init__()
self.num_queries = 300
def forward(self, enc_outputs_class):
_, topk_ind = torch.topk(
enc_outputs_class.max(-1).values, self.num_queries, dim=1
)
gather_index = topk_ind.unsqueeze(-1)
return gather_index
def main():
model = Model().cuda()
model.eval()
enc_outputs_class = torch.randn(1, 8400, 80).cuda()
inputs = [
torch_tensorrt.Input(enc_outputs_class.shape),
]
enabled_precisions = {torch.half, torch.float32}
trt_model = torch_tensorrt.compile(
model,
inputs=inputs,
enabled_precisions=enabled_precisions,
truncate_long_and_double=True,
min_block_size=1,
)
if __name__ == "__main__":
main()
so it seems like it has something to do with topk
.
from tensorrt.
Adding output_format="torchscript"
seems to solve the issue:
import torch
import torch_tensorrt
class Model(torch.nn.Module):
def __init__(self):
super().__init__()
self.num_queries = 300
def forward(self, enc_outputs_class):
_, topk_ind = torch.topk(
enc_outputs_class.max(-1).values, self.num_queries, dim=1
)
gather_index = topk_ind.unsqueeze(-1)
return gather_index
def main():
model = Model().cuda()
model.eval()
enc_outputs_class = torch.randn(1, 8400, 80).cuda()
inputs = [
torch_tensorrt.Input(enc_outputs_class.shape),
]
enabled_precisions = {torch.half, torch.float32}
trt_model = torch_tensorrt.compile(
model,
inputs=inputs,
enabled_precisions=enabled_precisions,
truncate_long_and_double=True,
min_block_size=1,
output_format="torchscript",
)
if __name__ == "__main__":
main()
from tensorrt.
Related Issues (20)
- 🐛 [Bug] RuntimeError: [Error thrown at core/util/trt_util.cpp:320] Expected type to be true but got false HOT 2
- ✨[Feature] Autogen TRT Plugins
- 🐛 [Bug] Nightly import fails HOT 2
- ❓ [Question] Model inference is much slower after updating to TensorRT 9.3 HOT 1
- 🐛 [Bug] failed to install torch-tensorrt HOT 1
- 🐛 [Bug] error: backend='torch_tensorrt' raised: TypeError: pybind11::init(): factory function returned nullptr HOT 4
- aten.atan2.out
- ❓ [Question] How to specific aten operators must be run by LibTorch in C++? HOT 7
- 🐛 [Bug] Llama-2-7b on a 4090 GPU
- Add support for `torch.ops.aten.baddbmm.default`
- Add support for `torch.ops.aten.full_like.default`
- Remove `ShapeProp` Pass
- 🐛 [Bug] A Segmentation fault occurs when torchtrt::ts::compile using Torch-TensorRT HOT 2
- 🐛 [Bug] torch.export fails to export embedding_bag_aten layer in a standalone test HOT 2
- ↔ [Converter] Add support for aten.diagonal
- 🐛 [Bug] Unable to freeze tensor of type Int64/Float64 into constant layer HOT 4
- 🐛 [Bug] `aten.scatter.value` converter error HOT 2
- `aten.resize_`
- `aten.diagonal`
- 🐛 [Bug] select_scatter decomposition caused compilation failure
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tensorrt.