Optimised Caffe with OpenCL supporting for less powerful devices such as mobile phones
-
Updated
Mar 12, 2019 - C++
#
fp16
Here are 32 public repositories matching this topic...
Let's train CIFAR 10 Pytorch with Half-Precision!
-
Updated
Oct 25, 2019 - Python
apextrainer is an open source toolbox for fp16 trainer based on Detectron2 and Apex
-
Updated
Feb 26, 2020 - Python
Simple Example of Pytorch -> TensorRT and Inference
-
Updated
Mar 20, 2021 - Jupyter Notebook
Converts a floating-point number or hexadecimal representation of a floating-point numbers into various formats and displays them into binary/hexadecimal.
-
Updated
Dec 23, 2021 - C
Round matrix elements to lower precision in MATLAB
matlab matrix arithmetic ieee rounding half-precision fp16 binary16 bfloat16 arithmetic-formats precisions subnormal-numbers
-
Updated
Jun 14, 2022 - MATLAB
Pytorch implementation of DreamerV2: Mastering Atari with Discrete World Models, based on the original implementation
-
Updated
Jul 25, 2022 - Python
IEEE 754-style floating-point converter
-
Updated
Jan 30, 2023 - TypeScript
Export pytorch model to ONNX and convert ONNX from float32 to float 16
-
Updated
Feb 2, 2023 - Python
Deploy stable diffusion model with onnx/tenorrt + tritonserver
docker machine-learning deploy transformers inference python3 pytorch nvidia fp16 tensorrt onnx triton-inference-server tensorrt-inference stablediffusion
-
Updated
Aug 15, 2023 - Jupyter Notebook
A flexible utility for converting tensor precision in PyTorch models and safetensors files, enabling efficient deployment across various platforms.
machine-learning deep-learning utilities deployment toolkit optimization pytorch fp16 model-compression model-conversion model-checkpoint bf16 tensor-precision efficient-deployment
-
Updated
Aug 24, 2023 - Python
👀 Apply YOLOv8 exported with ONNX or TensorRT(FP16, INT8) to the Real-time camera
-
Updated
May 23, 2024 - Python
Transformer implementation in pytorch trained on NVIDIA A100 in fp16
-
Updated
Jan 19, 2025 - Python
InsightFace REST API for easy deployment of face recognition services with TensorRT in Docker.
docker gpu face-recognition face-detection fp16 tensorrt onnx arcface insightface fastapi retinaface centerface mask-detection tensorrt-conversion scrfd yolov5-face adaface
-
Updated
Jun 1, 2025 - Python
llama 3.2 1b fp16 cpu inference in one file of pure VB.NET
inference llama vb-net vbnet fp16 inference-engine visual-basic-net basic-programming model-serving cpu-inference llm llms visual-basic-dot-net llm-serving llm-inference llama3 llama3-2
-
Updated
Jun 14, 2025 - Visual Basic .NET
Conversion to/from half-precision floating point formats
-
Updated
Aug 16, 2025 - C++
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.
performance-engineering deep-learning reproducible-research cuda pytorch fp16 cupy mixed-precision nsight gpu-benchmark nvtx fp32 tensor-core
-
Updated
Sep 5, 2025 - Python
🎬 Explore GPU training efficiency with FP32 vs FP16 in this modular lab, utilizing Tensor Core acceleration for deep learning insights.
performance-engineering deep-learning reproducible-research cuda pytorch fp16 cupy mixed-precision nsight gpu-benchmark nvtx fp32 tensor-core
-
Updated
Sep 6, 2025 - Python
Multimodal search engine using CLIP embeddings for bidirectional image-text retrieval.
search-engine scikit-learn foss jupyter-notebook python3 memory-management image-to-text batch-processing text-to-image fp16 gpu-optimization multimodal-deep-learning flickr8k-dataset bidirectional-search local-first sentence-transformers poetry-python gradio-interface clip-vit-b-16
-
Updated
Sep 9, 2025 - Jupyter Notebook
Improve this page
Add a description, image, and links to the fp16 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the fp16 topic, visit your repo's landing page and select "manage topics."