inference-performance

ML model optimization product to accelerate inference.

Benchmark llama.cpp on your own GPU/CPU boxes and compare against everyone else's — sweep runner, an sha256-keyed index of ~4M GGUF files, and a shared results database you query in plain language. Self-host it, or plug a machine into llamatoaster.com.

A simple tensorflow C++ REST API server

Inference Time Performance stats for various backbone networks.

Benchmarking the impact of compiler-level graph optimizations on NPU inference performance and memory wall bottlenecks.

Optimising train, inference and throughput of expensive ML models

Linear and Multiple Regression with data manipulation using SQL and R functions.

Check the fastText's inference performance for OOV.