Measure execution times of BERT models using WebGPU and WASM
Evaluate and submit AI model results for Frugal AI Challenge
Run benchmarks on prediction models
Browse and evaluate language models
Compare and rank LLMs using benchmark scores
Open Persian LLM Leaderboard
View and submit LLM benchmark evaluations
Quantize a model for faster inference
Predict customer churn based on input details
Browse and submit model evaluations in LLM benchmarks
Analyze model errors with interactive pages
Calculate survival probability based on passenger details
Explore and manage STM32 ML models with the STM32AI Model Zoo dashboard
The WebGPU Embedding Benchmark is a tool designed to measure the execution times of BERT models using WebGPU and WebAssembly (WASM). It provides a comprehensive way to evaluate and compare the performance of embedding models across different frameworks and configurations. By leveraging WebGPU's advanced capabilities, the benchmark helps developers optimize their machine learning workflows for better efficiency and speed.
npm install
npm start
What is BERT embeddings and why is it important?
BERT (Bidirectional Encoder Representations from Transformers) embeddings are vector representations of text that capture semantic meaning. They are widely used in natural language processing tasks for improved model accuracy and efficiency.
How do I interpret the benchmark results?
Results show execution times (e.g., inference time per batch) and other metrics. Lower times indicate better performance. Use these metrics to compare frameworks, models, or hardware configurations.
Which frameworks are supported?
The benchmark supports popular frameworks like TensorFlow, PyTorch, and ONNX. Additional frameworks can be added through configuration or plugins.