Comments (2)
One more (unrelated) issue is that performance of exported model, when called from python, is a bit slower than both eager evaluation, and torch.compile (which is the fastest, ignoring compilation time), although it's a small model. I was hoping it would be similar in performance to torch.compile -- just curious if this is expected?
Note that if you run exported model directly, it won't be performant by default because we are just running it op by op. To get it optimized, it's better to use a backend such as torch._inductor.aot_compile.
from pytorch.
One more (unrelated) issue is that performance of exported model, when called from python, is a bit slower than both eager evaluation, and torch.compile (which is the fastest, ignoring compilation time), although it's a small model. I was hoping it would be similar in performance to torch.compile -- just curious if this is expected?
from pytorch.
Related Issues (20)
- [inductor][cpu]mobilenet_v3_large PTQ/QAT performance regression in 2024-05-04 nightly release
- Aborted (core dumped) in torch.fft.irfftn/hfftn/ihfftn with malloc(): corrupted top size HOT 1
- DISABLED test_inline_dict_function_cpp_guard_manager (__main__.CppGuardManagerMiscTests) HOT 2
- DISABLED test_quantization_doc_ptdq (__main__.TestQuantizationDocs) HOT 1
- DISABLED test_quantization_doc_custom (__main__.TestQuantizationDocs) HOT 1
- DISABLED test_quantization_doc_ptsq (__main__.TestQuantizationDocs) HOT 1
- DISABLED test_quantization_doc_fx (__main__.TestQuantizationDocs) HOT 2
- DISABLED test_view_and_inplace_view (__main__.TestAOTAutograd) HOT 1
- [inductor][cpu]mobilenet_v2_quantized_qat float32 single thread static/dynamic shape CPP/default wrapper performance regression in 2024-04-28 nightly release HOT 1
- [BUG]Nan in gradients of scaled_dot_product_attention operation with mem_efficient backend
- Unnecessary warning when numpy not installed
- [RFC] Add Cpp Template for GEMM related ops via max-autotune for Inductor CPU
- MAX-Autotune Compilation Time Regression Due To Added MM Configs HOT 1
- cnm
- DISABLED [WORKFLOW_NAME] / [PLATFORM_NAME] / [JOB_NAME] HOT 1
- cnm
- [Dynamo] Support tracing through _get_current_dispatch_mode_stack HOT 3
- Have config/env option to disable all PT2 caching
- [dynamo] fix nn.Module @property that accesses closure cells
- KINETO_USE_DAEMON causing issues
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 pytorch.