saymrwulf/pytorch
1
0
Fork 0
mirror of https://github.com/saymrwulf/pytorch.git synced 2026-05-14 20:57:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
pytorch/benchmarks
History
Weizhuo Zhang 5153550e4b [CI] Add FP32 dynamic, AMP static, AMP dynamic for AOT inductor accuracy CPU CI test (#132836) 
This PR added 3 more accuracy test for AOT inductor CPU side.
1. FP32 dynamic shape accuracy test, torchbench suite
2. AMP static shape accuracy test, torchbench suite
3. AMP dynamic shape accuracy test, torchbench suite

**Test Time cost:**
| Precision 	| Shape Type 	| Suite      	| Time cost 	|
|-----------	|------------	|------------	|-----------	|
| FP32      	|    dynamic 	| Torchbench 	|  1h40m         	|
| AMP       	|     Static 	| Torchbench 	|  1h38m        	|
| AMP       	|    dynamic 	| Torchbench 	|  1h48m        	|

Pull Request resolved: https://github.com/pytorch/pytorch/pull/132836
Approved by: https://github.com/desertfire
2024-08-19 14:26:48 +00:00
..
distributed [BE][Easy][3/19] enforce style for empty lines in import segments in benchmarks/ (#129754) 2024-07-17 14:34:42 +00:00
dynamo [CI] Add FP32 dynamic, AMP static, AMP dynamic for AOT inductor accuracy CPU CI test (#132836) 2024-08-19 14:26:48 +00:00
fastrnns [BE][Easy][3/19] enforce style for empty lines in import segments in benchmarks/ (#129754) 2024-07-17 14:34:42 +00:00
framework_overhead_benchmark [BE][Easy][3/19] enforce style for empty lines in import segments in benchmarks/ (#129754) 2024-07-17 14:34:42 +00:00
functional_autograd_benchmark [BE][Easy] enable ruff rule PIE790: unnecessary pass statement (#133200) 2024-08-15 15:50:19 +00:00
fuser [BE][Easy][3/19] enforce style for empty lines in import segments in benchmarks/ (#129754) 2024-07-17 14:34:42 +00:00
gpt_fast [BC breaking] move benchmarking + prefer inductor path (#132827) 2024-08-08 00:47:45 +00:00
inference [BE][Easy][3/19] enforce style for empty lines in import segments in benchmarks/ (#129754) 2024-07-17 14:34:42 +00:00
instruction_counts Add instruction count benchmark to run on pull requests (#131475) 2024-08-12 05:20:26 +00:00
nested
operator_benchmark remove benchmarks/__init__.py (#133390) 2024-08-15 19:08:10 +00:00
overrides_benchmark [BE][Easy][3/19] enforce style for empty lines in import segments in benchmarks/ (#129754) 2024-07-17 14:34:42 +00:00
profiler_benchmark [BE][Easy][3/19] enforce style for empty lines in import segments in benchmarks/ (#129754) 2024-07-17 14:34:42 +00:00
record_function_benchmark
serialization [BE][Easy][3/19] enforce style for empty lines in import segments in benchmarks/ (#129754) 2024-07-17 14:34:42 +00:00
sparse [BC breaking] move benchmarking + prefer inductor path (#132827) 2024-08-08 00:47:45 +00:00
static_runtime [9/N] Replace c10::optional with std::optional (#130674) 2024-07-15 00:48:43 +00:00
tensorexpr [BE][Easy][3/19] enforce style for empty lines in import segments in benchmarks/ (#129754) 2024-07-17 14:34:42 +00:00
transformer Add explicit GQA support. (#131559) 2024-08-09 21:25:35 +00:00
compare-fastrnn-results.py [BE][Easy][3/19] enforce style for empty lines in import segments in benchmarks/ (#129754) 2024-07-17 14:34:42 +00:00
compare.sh
README.md
upload_scribe.py

README.md

PyTorch Benchmarks

This folder contains scripts that produce reproducible timings of various PyTorch features.

It also provides mechanisms to compare PyTorch with other frameworks.

Setup environment

Make sure you're on a machine with CUDA, torchvision, and pytorch installed. Install in the following order:

# Install torchvision. It comes with the pytorch stable release binary
conda install pytorch torchvision -c pytorch

# Install the latest pytorch master from source.
# It should supersede the installation from the release binary.
cd $PYTORCH_HOME
python setup.py build develop

# Check the pytorch installation version
python -c "import torch; print(torch.__version__)"

Benchmark List

Please refer to each subfolder to discover each benchmark suite. Links are provided where descriptions exist: