Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Repository Index
47,133 repositories indexed
1–24 of 24 · Most stars
Machine Learning Engineering Open Book
CUDA on non-NVIDIA GPUs
- cuda
- rust
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
John the Ripper jumbo - advanced offline password cracker, which supports hundreds of hash and cipher types, and runs on many operating systems, CPUs, GPUs, and even some FPGAs
- john
- c
- ripper
- password
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
- tensorrt
- nvidia
- deep-learning
- inference
A minimal GPU design in Verilog to learn how GPUs work from the ground up
Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.
- onednn
- oneapi
- performance
- cpp
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
Experimental DLSS Multi Frame Generation controls for any supported MFG title on RTX 40 series GPUs
ThunderSVM: A Fast SVM Library on GPUs and CPUs
- classification
- regression
- one-class-learning
- cuda
ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using Transformers Models.
Drop-in FSR 3.1 upscaler for Direct3D 12 that runs DLSS's network (Model E) on AMD GPUs
AMDNR Neural Rendering on AMD GPUs, built into OptiScaler: model interleave, residual composition, XeSS frame generation up to 6X, FSR Ray Regeneration. Discord: https://discord.gg/AMDNR · Ko-fi: https://ko-fi.com/3zinr
ThunderGBM: Fast GBDTs and Random Forests on GPUs
Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch). No cloud, no API key.
- apple-silicon
- audio-generation
- claude-code
- game-audio
Exascale multiphase flow solver — 2025 Gordon Bell Prize Finalist | 200T grid points on 43K+ GPUs
- gpu
- exascale
- cfd
- fortran
Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linux
- amd
- local-llm
- radeon
- realtime
Bolt is a C++ template library optimized for GPUs. Bolt provides high-performance library implementations for common algorithms such as scan, reduce, transform, and sort.
Unlock full speed FP16 tensor core of NVIDIA Turing GPUs
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
- calibration
- cuda
- cuda-graphs
- decision-making
Load a modified VBIOS for NVIDIA GPUs on Windows through the driver's registry override, without flashing
DCompute: Native execution of D on GPUs and other Accelerators
2D triangulation library. Allows translating lines and polygons (both based on points) to the language of GPUs.
- triangulation
- computational-geometry
- golang