Comments (5)
OptimizedModule
is an artifact of torch.compile
compilation. We don't have a way to save those models. Instead, ir=dynamo
is the way to go if you want to serialize models.
The following isn't the recommended workflow. torch_tensorrt.dynamo.export
can only take torch.fx.GraphModule
as its input.
trt_exp_program = torch_tensorrt.dynamo.export(trt_mod, [dummy_x.half(), dummy_embed.half()], "ep")
The docs you linked isn't updated (we are working on fixing the docs). Please refer to this file https://github.com/pytorch/TensorRT/blob/release/2.2/docsrc/user_guide/saving_models.rst
from tensorrt.
@gs-olive any chance you can help with this?
from tensorrt.
Hi @peri044,
I tried your suggestion (using dynamo
as the ir_mode
) but ended up with the following error:
torch._dynamo.exc.UserError: Dynamic control flow is not supported at the moment. Please use functorch.experimental.control_flow.cond to explicitly capture the control flow.
dynamo
compile does not act like jit.script
? shouldn't it handle logic conditions?
What if I want it to act like jit.trace
where only the flow activated for the specific input is compiled?
Just a reminder using torch_compile
as ir_mode
compiles the model but produces OptimizedModule
.
If it helps I can share my code and also promoting the pytorch version is an option (if this issue is fixed/supported in later versions).
from tensorrt.
@gs-olive @peri044
Can you please help?
from tensorrt.
Hi - to my knowledge, Torch's Dynamo export tracer works slightly differently to torch.jit.trace
, in that torch.jit.trace
generally traces only the control flow for the specific input, as you mentioned, and effectively collapses the if
/else
statements. Dynamo export's tracer can sometimes try to trace without modifying the conditional, which leads to errors like this where it requires a specific tracer-friendly conditional to work.
I believe there are tools to do this "conditional-flattening" in advance - maybe something like torch.fx.experimental.proxy_tensor.make_fx
or torch.fx.symbolic_trace
with concrete_args
specified. Then, once traced with control flow removed, this FX graph can be passed to torch_tensorrt.compile
. @peri044 - do you know of any other methods for accomplishing this?
Providing the source code/sample model would be helpful for us to debug further as well.
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 2
- 🐛 [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 3
- `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.