An AI-powered MLOps assistant for effortless model compression. Upload PyTorch models to chat with a local LLM expert, receive hardware-aware optimization advice, and perform one-click FP16/INT8 quantization to reduce model size and latency.

Comprehensive performance analysis of DeepSeek V3 quantization levels (FP16, Q8_0, Q4_0) on 16GB GPU environments.

llama 3.2 1b fp16 cpu inference in one file of pure VB.NET

Implémentation algorithmique du format FP16 (IEEE-754) en C

16-bit Floating Point Unit implementation in Verilog

A flexible utility for converting tensor precision in PyTorch models and safetensors files, enabling efficient deployment across various platforms.

Custom Speech Note configuration with FP16 and q8_0 WhisperCpp models for improved speech-to-text accuracy.

A reproducible GPU benchmarking lab that compares FP16 vs FP32 training on MNIST using PyTorch, CuPy, and Nsight profiling tools. This project blends performance engineering with cinematic storytelling—featuring NVTX-tagged training loops, fused CuPy kernels, and a profiler-driven README that narrates the GPU’s inner workings frame by frame.

First super-resolution model designed for Apple Neural Engine. 2x upscale, real-time, on-device. Built by Ben Racicot.

Transformer implementation in pytorch trained on NVIDIA A100 in fp16

Hands-on GPU inference acceleration experiments across Jetson and cloud GPUs using ONNX Runtime, TensorRT, FP16, and model benchmarks.

A minimal, high-performance starter kit for running AI model inference on NVIDIA GPUs using CUDA. Includes environment setup, sample kernels, and guidance for integrating ONNX/TensorRT pipelines for fast, optimized inference on modern GPU hardware.

40x faster AI inference: ONNX to TensorRT optimization with FP16/INT8 quantization, multi-GPU support, and deployment

Multimodal search engine using CLIP embeddings for bidirectional image-text retrieval.

Build, run, and setup scripts for the complete TensorRT-LLM pipeline on RTX A6000 Ada (SM89). Reproducible path from HuggingFace checkpoint to deployable .engine file, with FP16 baseline and FP8 quantization. Companion material to the 4-part blog series on ai-box.eu — in preparation for the NVIDIA TensorRT Edge-LLM ecosystem.

PointPillars TensorRT FP16 on Jetson AGX Orin | 42 FPS / <24ms | ByteTrack 3D MOT 78.4% MOTA | 3.8x speedup

The floats package provides types for handling multi-precision floating-point numbers.

🎬 Explore GPU training efficiency with FP32 vs FP16 in this modular lab, utilizing Tensor Core acceleration for deep learning insights.

基于TensorRT加速的YOLOv5高性能推理框架 | High-performance YOLOv5 inference framework accelerated by TensorRT with dynamic optimization

The goal of this reposotory is create a downcasting the Fashion MNIST model from FP32 to FP16 using pytorch