inference

Model benchmarking suite

Measures the performance of deep learning models in various deployment scenarios.

Reference implementations of MLPerf™ inference benchmarks

GitHub
1k stars
57 watching
536 forks
Language: Python
last commit: 5 days ago
Linked from 1 awesome list

benchmarkmachine-learning

Screenshot of mlcommons/inference website

mlcommons.org/en/groups/inference

Backlinks from these awesome lists:

Related projects:

Repository Description Stars
szilard/benchm-ml A benchmark for evaluating machine learning algorithms' performance on large datasets 1,869
microsoft/private-benchmarking A platform for private benchmarking of machine learning models with different trust levels. 6
nikolaydubina/go-ml-benchmarks A benchmarking project comparing performance of different machine learning inference frameworks and models on Go platform 30
microsoft/0xdeca10b A framework for hosting and training machine learning models on a blockchain, enabling secure sharing and prediction without requiring users to pay for data or model updates. 556
freedomintelligence/mllm-bench Evaluates and compares the performance of multimodal large language models on various tasks 55
utensor/utensor A lightweight machine learning inference framework built on Tensorflow optimized for Arm targets. 1,729
ailab-cvc/seed-bench A benchmark for evaluating large language models' ability to process multimodal input 315
mosecorg/mosec A high-performance ML model serving framework 790
aronchick/mlops-pipeline Automates the end-to-end machine learning workflow from code commit to model deployment 18
mazhar-ansari-ardeh/benchmarkfcns Provides benchmarking functions for mathematical optimization algorithms 66
oxid15/cascade A lightweight MLOps library for small teams and individuals to manage machine learning model development lifecycle 22
catboost/benchmarks Comparative benchmarks of various machine learning algorithms 169
ecoapm/benchmarkmocknet Comparing performance of various .NET mocking libraries using BenchmarkDotNet 22
aifeg/benchlmm An open-source benchmarking framework for evaluating cross-style visual capability of large multimodal models 83
python/pyperformance An authoritative source of real-world benchmarks for Python implementations. 869