Measure execution times of BERT models using WebGPU and WASM
Open Persian LLM Leaderboard
Convert Hugging Face models to OpenVINO format
Find and download models from Hugging Face
View LLM Performance Leaderboard
Merge machine learning models using a YAML configuration file
Convert Stable Diffusion checkpoint to Diffusers and open a PR
Display LLM benchmark leaderboard and info
Rank machines based on LLaMA 7B v2 benchmark results
Submit models for evaluation and view leaderboard
Push a ML model to Hugging Face Hub
Display model benchmark results
Convert Hugging Face model repo to Safetensors
WebGPU Embedding Benchmark is a tool designed to measure the execution times of BERT models using WebGPU and WebAssembly (WASM). It helps developers and researchers evaluate the performance of embedding models in web-based environments, leveraging modern graphics technologies for accelerated computations.
• WebGPU Acceleration: Leverages WebGPU for hardware-accelerated computations. • WASM Execution: Utilizes WebAssembly for efficient model inference. • Detailed Timing Measurements: Provides precise execution time metrics for model inference. • Cross-Platform Compatibility: Runs on modern web browsers supporting WebGPU. • Model Optimization Insights: Offers benchmarks to guide model optimization strategies. • Performance Comparison: Enables comparison of performance across different hardware setups.
What does WebGPU Embedding Benchmark measure?
It measures the execution time of BERT models using WebGPU and WASM, providing insights into performance bottlenecks.
Which browsers support WebGPU?
As of now, browsers like Chrome, Firefox, and Edge provide experimental or full support for WebGPU.
Why is WebGPU combined with WASM for this benchmark?
WebGPU offers hardware acceleration, while WASM provides efficient computation, making them a powerful combination for high-performance web-based model inference.