likelovewantlikelovewant/ollama-for-amd/AGENTS.md

ollama-for-amd

AGENTS.md1.8k starsChanged 10 months agoMITView on GitHub

For a full build from the repository root: For quick Go-only iteration against an existing native payload: See docs/development.md for prerequisites, platform notes, GPU backends, and the full development workflow.

1 other project uses a version of this.

Adopted by

Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Sep 2026Oct 2026Nov 2026

New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.

Most recently taken up by

ollama/ollamaword for word, first seen Oct 8, 2026

Who's talking about likelovewant/ollama-for-amd

The biggest 5 of 12 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 12

Talked about on GitHub (12 times).

On GitHub · 12

Feb 4, 2025Empty supported_types list prevents GPU detection for older AMD GPUs (RX 5700 XT) in official Ollama distribution — ollama/ollama3 reactions · 3 comments
May 18, 2025gfx1030 is an officially supported architecture, yet its not available as an installable package — ByronLeeeee/Ollama-For-AMD-Installer1 reaction · 3 comments
Mar 8, 2026ROCm error: invalid device function in ggml_cuda_mul_mat_q on RX 6750 GRE (gfx1031) with ollama-for-amd patch on Windows — ollama/ollama0 reactions · 2 comments
Oct 9, 2025Broken for 6750XT — ByronLeeeee/Ollama-For-AMD-Installer0 reactions · 5 comments
Aug 25, 2025使用本地部署模型时翻译报错 — PDFMathTranslate-next/PDFMathTranslate-next0 reactions · 2 comments

7 more on GitHub

Apr 26, 2025"ggml_cuda_compute_forward: SCALE failed > ROCm error: invalid device function" when running with 6750XT with Windows 10 — ollama/ollama0 reactions · 1 comment
Mar 14, 2025was there a bad update to onnxruntime? — lamikr/rocm_sdk_builder0 reactions · 4 comments
Mar 3, 2025Gpu cores=8 but "no compatible GPUs were discovered" — likelovewant/ROCmLibs-for-gfx1103-AMD780M-APU0 reactions · 1 comment
Feb 13, 2025ollama deepseek-r1 with amd gpu vega56, fine tuning with transformer — aquaxysgit/deepseek0 reactions
Feb 7, 2025ollama with deepseek-r1 support amd vega56 GPU — aquaxysgit/deepseek0 reactions
Feb 6, 2025ollama (+gpu)를 이용한 deepseek-R1 오프라인 설치 — aquaxysgit/deepseek0 reactions
Dec 29, 2024言論20241220 — cutepig123/gitblog0 reactions

Other versions1 project uses a version of this.
Word for word · 1
ollama/ollama★ 186k100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- CLAUDE.mdCLAUDE.md

The file

Create a free account to mount

Files

AGENTS.md

Building

For a full build from the repository root:

cmake -B build .
cmake --build build --parallel 8
./ollama serve

For quick Go-only iteration against an existing native payload:

go build .
go run . serve

See docs/development.md for prerequisites, platform notes, GPU backends, and the full development workflow.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free