-
ort
A safe Rust wrapper for ONNX Runtime 1.20 - Optimize and accelerate machine learning inference & training
-
opencl3
Khronos OpenCL 3.0 API and extensions
-
blitzar
High-Level Rust wrapper for the blitzar-sys crate
-
fast-umap
Configurable UMAP (Uniform Manifold Approximation and Projection) in Rust
-
crabslab
Slab allocator focused on GPU compute (rust-gpu)
-
burn-tch
LibTorch backend for the Burn framework using the tch bindings
-
kn-cuda-eval
A CUDA executor for neural network graphs
-
RayBNN_Raytrace
Ray tracing library using GPUs, CPUs, and FPGAs via CUDA, OpenCL, and oneAPI
-
pumas
A power usage monitor for Apple Silicon
-
kn-cuda-sys
A wrapper around the CUDA APIs
-
kn-graph
A neural network inference graph intermediate representation, with surrounding utilities
-
kn-runtime
Dynamic wrapper around CPU and GPU inference
-
femto-gpt
Minimal Rust library for training GPT language-models
-
nvtx
Rust bindings for the NVIDIA® Tools Extension SDK (NVTX)
-
onnxruntime-sys-ng
Unsafe wrapper around Microsoft's ONNX Runtime
-
host_discovery
host discovery
-
onnxruntime-ng
Wrapper around Microsoft's ONNX Runtime
-
raybnn
RayBNN
-
jetson_nano_monitor
A Rust-based monitoring tool for Jetson Nano to track CPU, GPU, RAM, and temperature metrics
-
ai-dataloader
PyTorch DataLoader
-
bevy_firework
CPU-driven, batch-rendered particle system for the Bevy game engine
-
mtemp
CLI for monitoring temperatures
-
img_rcc
image processing with CUDA, C++
-
onnxruntime
Wrapper around Microsoft's ONNX Runtime
-
RayBNN_Cell
Cell Position Generator for RayBNN
-
system-info-lite
getting system information, including CPU, GPU, RAM, and OS information
-
juice
Machine Learning Framework for Hackers
-
RayBNN_Optimizer
Gradient Descent Optimizers and Genetic Algorithms using GPUs, CPUs, and FPGAs via CUDA, OpenCL, and oneAPI
-
forma-render
An efficient vector-graphics renderer
-
tfhe-cuda-backend
Cuda implementation of TFHE-rs primitives
-
rllama
Pure Rust implementation of LLaMA-family of models, executable
-
tvm
Rust frontend support for TVM
-
para-graph
"Para-Graph" delivers swift, parallel graph algorithms in Rust, optimized for CPU and GPU. Ideal for HPC workflows.
-
RayBNN_Neural
Neural Networks with Sparse Weights in Rust using GPUs, CPUs, and FPGAs via CUDA, OpenCL, and oneAPI
-
photo
High-precision rendering engine
-
smelte-rs
Efficient inference ML framework written in rust
-
concrete-cuda
Cuda implementation for the concrete FHE library
-
collenchyma
high-performance computation on any hardware
-
custos
A minimal OpenCL, WGPU, CUDA and host CPU array manipulation engine
-
machine-info
CPU, GPU and memory monitor. Use it to track resources usage
-
gradients
An OpenCL, CUDA and CPU based Deep Learning Library
-
memonitor
Query CPU and GPU memory information in a portable way
-
mcai-onnxruntime-sys
Unsafe wrapper around Microsoft's ONNX Runtime
-
ezstress
A crossplatform, device agnostic, easy to use GPU and CPU stress test cli tool
-
ulib
Universal data storage library for CPU/GPU heterogeneous applications
-
cust_core
Core library for cust that can be shared across CPU and GPU
-
tvm-rt
Rust bindings for the TVM runtime API
-
ucc
Universal compiler invocator for heterogeneous CPU/GPU computation applications
-
luminar
Manage computing resources for multiple users on single machine
-
eikon
High performance rendering engine. Supports both CPU and GPU rendering
Try searching with DuckDuckGo.