NanoGPT (124M) in 90 seconds
Repository Index
104,105 visible repositories in the index
1–24 of 31 · Most stars
Benchmarks of approximate nearest neighbor libraries in Python
XcodeBenchmark measures the compilation time of a large codebase on iMac, MacBook, and Mac Pro
Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention
Easy benchmarking of all publicly accessible implementations of convnets
Benchmarks for popular CNN models
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
Macrobenchmarking framework for Elasticsearch
PerfKit Benchmarker (PKB) contains a set of benchmarks to measure and compare cloud offerings. The benchmarks use default settings to reflect what most users will see. PerfKit Benchmarker is licensed under the Apache 2 license terms. Please make sure to read, understand and agree to the terms of the LICENSE and CONTRIBUTING files before proceeding.
Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
- vae
- benchmarking
- beta-vae
- comparison
A Fair and Scalable Time Series Forecasting Benchmark and Toolkit.
- time-series
- traffic-forecasting
- benchmarking
- long-time-series-forecasting
Reference implementations of MLPerf® training benchmarks
Reference implementations of MLPerf® inference benchmarks
:bar_chart: Benchmark multiple object trackers (MOT) in Python
- object-tracking
- object-detection
- clear-mot-metrics
- benchmark
pytest fixture for benchmarking code
- python
- pytest
- benchmark
- benchmarking
A comparison between some VPS providers. It uses Ansible to perform a series of automated benchmark tests over the VPS servers that you specify. It allows the reproducibility of those tests by anyone that wanted to compare these results to their own. All the tests results are available in order to provide independence and transparency.
- vps
- ansible
- comparison
- python
:chart_with_upwards_trend: Performance analysis for Python snippets
- python
- performance-analysis
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
- cifar10
- deep-learning
- experimentation
- machine-learning
基于SSRSpeed修改,支持同时进行单线程/多线程测速,并可同时进行流媒体解锁状态测试
FuzzBench - Fuzzer benchmarking as a service.
- fuzzing
- benchmarking
- benchmark-framework
- evaluation
The repository host gives no description.
Benchmark for vector databases.
- benchmark
- performance
- vector-database
- vector-search
Python Performance Benchmark Suite
- python
- performance
- benchmark
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
- ai-agents
- benchmarking
- llm-evaluation
- python