Search

Results

Integrated GPU support · Issue #2637 · ollama/ollama

[https://github.com/ollama/ollama/issues/2637] - 2024-05-02 05:26:58 - public:mzimmerm

amd, apu, gfx900, install, pytorch, rocm - 6 | id:1491350 -

Latest (0.1.27) docker image with ROCm works for me on Ryzen 5600G with 8GB VRAM allocation. Prompt processing is 2x faster than with CPU. Generation runs at max speed even if CPU is busy running other processes. I am on Fedora 39. Container setup: HSA_OVERRIDE_GFX_VERSION=9.0.0

SDB:AMD GPGPU - openSUSE Wiki

[https://en.opensuse.org/SDB:AMD_GPGPU#ROCm_-_Running_on_unsupported_hardware] - 2024-05-02 05:09:35 - public:mzimmerm

amd, apu, best, good, gpu, install, pytorch, rocm, tumbleweed - 9 | id:1491348 -

Use this to install ROCm on Tumbleweed. Does NOT talk about Pytorch, the tag is for completeness.

ROCm/pytorch at release/2.1_with_triton_fixes

[https://github.com/ROCm/pytorch/tree/release/2.1_with_triton_fixes] - 2024-03-22 03:28:54 - public:mzimmerm

amd, github, pytorch, repo, rocm - 5 | id:1490078 -

AMD's repo of Pytorch. This is the branch I succesfully built.

ROCm/pytorch: Tensors and Dynamic neural networks in Python with strong GPU acceleration

[https://github.com/ROCm/pytorch] - 2024-03-20 21:14:52 - public:mzimmerm

amd, github, pytorch, repo, rocm - 5 | id:1490028 -

AMD repo for their PyTorch version.

[rocm] No GPU support after rebuild with ROCm 6.0 (#6) · Issues · Arch Linux / Packaging / Packages / python-pytorch · GitLab

[https://gitlab.archlinux.org/archlinux/packaging/packages/python-pytorch/-/issues/6] - 2024-03-18 07:08:13 - public:mzimmerm

amd, apu, bug, gfx902, pytorch, rocm - 6 | id:1490001 -

This site seems to claim there is a known fix. Looks like someone is fixing it???

Installing PyTorch for ROCm — ROCm installation (Linux)

[https://rocm.docs.amd.com/projects/install-on-linux/en/develop/how-to/3rd-party/pytorch-install.html#testing-the-pytorch-installation] - 2024-03-18 06:11:47 - public:mzimmerm

amd, apu, best, gfx900, gfx902, good, install, pytorch, rocm - 9 | id:1489999 -

Installing PyTorch for ROCm - this document claims gfx900 compatibility

Index of /rocm/manylinux/

[https://repo.radeon.com/rocm/manylinux/] - 2024-03-16 23:13:52 - public:mzimmerm

amd, pytorch, repo, rocm, wheel - 5 | id:1489976 -

Pytorch packages from AMD. Goes with amdgpu-install packages in https://repo.radeon.com/amdgpu-install/

Document describing installation. The only supported claim: Ubuntu 22.04.3 Desktop Version with HWE Ubuntu kernel 6.5 Yes

[https://rocm.docs.amd.com/_/downloads/radeon/en/latest/pdf/] - 2024-03-15 08:48:59 - public:mzimmerm

amd, apu, install, pytorch, rocm - 5 | id:1489960 -

Install PyTorch for ROCm — Use ROCm on Radeon GPUs

[https://rocm.docs.amd.com/projects/radeon/en/latest/docs/install/install-pytorch.html] - 2024-03-08 01:45:24 - public:mzimmerm

amd, gpu, install, post, pytorch, rocm, validate - 7 | id:1489852 -

Install PyTorch corresponding to rocm versions from Pytorch prebuild by AMD. Also has post-install validation

Script for testing PyTorch support with AMD GPUs using ROCM

[https://gist.github.com/damico/484f7b0a148a0c5f707054cf9c0a0533] - 2024-03-08 01:01:10 - public:mzimmerm

amd, gpu, pytorch, rocm, test - 5 | id:1489851 -

Test for PyTorch and ROCm after installing ROCm.

AMD Extends Support for PyTorch Machine Learning Development on Select RDNA™ 3 GPUs with ROCm™ 5.7 | PyTorch

[https://pytorch.org/blog/amd-extends-support-for-pt-ml/] - 2024-03-06 05:53:10 - public:mzimmerm

amd, apu, install, pytorch, rocm - 5 | id:1489832 -

The links in “How to guide“ provide instructions that are hopeful. Maybe start with those instructions!

Doesn't ROCm support AMD's integrated GPU (APU)? · Issue #2216 · ROCm/ROCm

[https://github.com/ROCm/ROCm/issues/2216] - 2024-03-06 05:25:48 - public:mzimmerm

amd, apu, best, gfx902, good, gpu, install, pytorch, rocm - 9 | id:1489829 -

This guy claims successful installation of ROCm on Ubuntu - this seems to be workable for Tumbleweed as well. See the comment “nav9 commented on Jul 16, 2023“

Ditching CUDA for AMD ROCm for more accessible LLM training and inference. | by Rafael Manzano Masapanta | Medium

[https://medium.com/@rafaelmanzanom/ditching-cuda-for-amd-rocm-for-more-accessible-llm-inference-ryzen-apus-edition-92c3649f8f7d] - 2024-03-05 03:55:11 - public:mzimmerm

ai, amd, apu, compile, gfx902, install, pytorch, rocm - 8 | id:1489810 -

Train LLM on AMD APU. In this scenario, we’ll use an APU because most laptops with a Ryzen CPU include an iGPU; specifically, this post should work with iGPUs based on the “GCN 5.0” architecture, or “Vega” for friends. We’ll use an AMD Ryzen 2200G in this post, an entry-level processor equipped with 4C/4T and an integrated GPU.

Follow Tags

Pytorch - Please Log In To follow this tag
amd - Please Log In To follow this tag

Export:

JSON XML RSS

yabs.io

Yet Another Bookmarks Service