Measure execution times of BERT models using WebGPU and WASM
Visualize model performance on function calling tasks
Evaluate reward models for math reasoning
Pergel: A Unified Benchmark for Evaluating Turkish LLMs
Compare model weights and visualize differences
Convert Hugging Face model repo to Safetensors
Benchmark AI models by comparison
View NSQL Scores for Models
Track, rank and evaluate open LLMs and chatbots
Evaluate model predictions with TruLens
Convert Stable Diffusion checkpoint to Diffusers and open a PR
Calculate survival probability based on passenger details
Display and submit LLM benchmarks
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.