A high-throughput and memory-efficient inference and serving engine for LLMs
-
Updated
Oct 7, 2024 - Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Part of the stock-tracker series - Automated tracking tool for AMD stock price movements against predefined percentage targets.
PingPilot is a desktop app designed to speed up your online gaming experience by using ML models that processes packets, only using the NPU.
This repository contains scripts and commands for exporting YOLO models to different formats, including TensorRT (.engine) and ONNX (.onnx).
web UI for GPU-accelerated ONNX pipelines like Stable Diffusion, even on Windows and AMD
Stretching GPU performance for GEMMs and tensor contractions.
QualityScaler - image/video AI upscaler app
Stable Diffusion web UI
Machine Intelligence Shader Autogen. AMDGPU ML shader code generator. (previously iGEMMgen)
FluidFrames.RIFE | video AI frame-generation app
Voice-to-voice personal assistant, Full-local, GPU company agnostic.
ProcessorPy is a Cross-platform, Pure python Library that's will get CPU information's & specifications also it's provide a sensors readings for both Widnows and Linux-Debian systems
OpenCL integration for Python, plus shiny features
RealScaler - image/video AI upscaler app (Real-ESRGAN)
Add a description, image, and links to the amd topic page so that developers can more easily learn about it.
To associate your repository with the amd topic, visit your repo's landing page and select "manage topics."