pomoke / torch-apu-helperLinks
Make PyTorch models at least run on APUs.
☆56Updated last year
Alternatives and similar repositories for torch-apu-helper
Users that are interested in torch-apu-helper are comparing it to the libraries listed below
Sorting:
- ☆63Updated 4 months ago
- ☆474Updated last week
- ☆396Updated 6 months ago
- No-code CLI designed for accelerating ONNX workflows☆214Updated 3 months ago
- build scripts for ROCm☆185Updated last year
- ☆64Updated last year
- Deep Learning Primitives and Mini-Framework for OpenCL☆202Updated last year
- 8-bit CUDA functions for PyTorch☆63Updated 2 weeks ago
- ☆230Updated 2 years ago
- Reverse engineering the rk3588 npu☆95Updated last year
- Linux based GDDR6/GDDR6X VRAM temperature reader for NVIDIA RTX 3000/4000 series GPUs.☆104Updated 5 months ago
- The HIP Environment and ROCm Kit - A lightweight open source build system for HIP and ROCm☆438Updated this week
- Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.☆73Updated 8 months ago
- Inference engine for Intel devices. Serve LLMs, VLMs, Whisper, Kokoro-TTS over OpenAI endpoints.☆211Updated this week
- Onboarding documentation source for the AMD Ryzen™ AI Software Platform. The AMD Ryzen™ AI Software Platform enables developers to take…☆81Updated this week
- My develoopment fork of llama.cpp. For now working on RK3588 NPU and Tenstorrent backend☆108Updated last week
- DLPrimitives/OpenCL out of tree backend for pytorch☆373Updated last year
- AMD (Radeon GPU) ROCm based setup for popular AI tools on Ubuntu 24.04.1☆211Updated 3 weeks ago
- Because RKNPU only knows 4D☆37Updated last year
- 8-bit CUDA functions for PyTorch, ported to HIP for use in AMD GPUs☆51Updated 2 years ago
- ☆148Updated last week
- ☆42Updated 2 years ago
- Download models from the Ollama library, without Ollama☆100Updated 10 months ago
- General Site for the GFX803 ROCm Stuff☆117Updated last month
- Run Large Language Models on RK3588 with GPU-acceleration☆117Updated 2 years ago
- General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). …☆52Updated 7 months ago
- ☆53Updated last year
- AMD related optimizations for transformer models☆90Updated last month
- A set of utilities for monitoring and customizing GPU performance☆153Updated last year
- ☆46Updated last week