LukasHedegaard/pytorch-benchmark
Easily benchmark PyTorch model FLOPs, latency, throughput, allocated gpu memory and energy consumption
This tool helps machine learning engineers and researchers compare the efficiency of different PyTorch models. By providing your model and a sample input, it measures key performance metrics like floating-point operations (FLOPs), inference speed (latency and throughput), and GPU memory usage. This allows you to understand how well your models will perform in a production environment or on resource-constrained devices.
109 stars. Used by 1 other package. No commits in the last 6 months. Available on PyPI.
Use this if you need to objectively compare multiple PyTorch models based on their computational cost and speed, or optimize an existing model for better performance.
Not ideal if you're looking for deep profiling tools that identify specific bottlenecks within your model's code, or if you are not working with PyTorch models.
Stars
109
Forks
11
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 25, 2023
Commits (30d)
0
Dependencies
8
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LukasHedegaard/pytorch-benchmark"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
triton-inference-server/server
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
gpu-mode/Triton-Puzzles
Puzzles for learning Triton
hailo-ai/hailo_model_zoo
The Hailo Model Zoo includes pre-trained models and a full building and evaluation environment
open-mmlab/mmdeploy
OpenMMLab Model Deployment Framework
hyperai/tvm-cn
TVM Documentation in Chinese Simplified / TVM 中文文档