autonomoususer

cross-posted from: https://lemmy.world/post/27088416

This is an update to a previous post found at https://lemmy.world/post/27013201

---

Ollama uses the AMD ROCm library which works well with many AMD GPUs not listed as compatible by forcing an LLVM target.

The original Ollama documentation is wrong as the following can not be set for individual GPUs, only all or none, as shown at github.com/ollama/ollama/issues/8473

AMD GPU issue fix

1. Check your GPU is not already listed as compatibility at github.com/ollama/ollama/blob/main/docs/gpu.md#linux-support
2. Edit the Ollama service file. This uses the text editor set in the $SYSTEMD_EDITOR environment variable.

sudo systemctl edit ollama.service

3. Add the following, save and exit. You can try different versions as shown at github.com/ollama/ollama/blob/main/docs/gpu.md#overrides-on-linux

[Service]
Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0"

4. Restart the Ollama service.

sudo systemctl restart ollama

cross-posted from: https://lemmy.world/post/27088416

This is an update to a previous post found at https://lemmy.world/post/27013201

---

Ollama uses the AMD ROCm library which works well with many AMD GPUs not listed as compatible by forcing an LLVM target.

The original Ollama documentation is wrong as the following can not be set for individual GPUs, only all or none, as shown at github.com/ollama/ollama/issues/8473

AMD GPU issue fix

1. Check your GPU is not already listed as compatibility at github.com/ollama/ollama/blob/main/docs/gpu.md#linux-support
2. Edit the Ollama service file. This uses the text editor set in the $SYSTEMD_EDITOR environment variable.

sudo systemctl edit ollama.service

3. Add the following, save and exit. You can try different versions as shown at github.com/ollama/ollama/blob/main/docs/gpu.md#overrides-on-linux

[Service]
Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0"

4. Restart the Ollama service.

sudo systemctl restart ollama

This is an update to a previous post found at https://lemmy.world/post/27013201

Ollama uses the AMD ROCm library which works well with many AMD GPUs not listed as compatible by forcing an LLVM target.

The original Ollama documentation is wrong as the following can not be set for individual GPUs, only all or none, as shown at github.com/ollama/ollama/issues/8473

AMD GPU issue fix

1. Check your GPU is not already listed as compatibility at github.com/ollama/ollama/blob/main/docs/gpu.md#linux-support
2. Edit the Ollama service file. This uses the text editor set in the $SYSTEMD_EDITOR environment variable.

sudo systemctl edit ollama.service

3. Add the following, save and exit. You can try different versions as shown at https://github.com/ollama/ollama/blob/main/docs/gpu.md#overrides-on-linux

[Service]
Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0"

4. Restart the Ollama service.

sudo systemctl restart ollama

cross-posted from: https://lemmy.world/post/27013201

Ollama lets you download and run large language models (LLMs) on your device.

Install Ollama on Arch Linux (Windows guide coming soon)

1. Check whether your device has an AMD GPU, NVIDIA GPU, or no GPU. A GPU is recommended but not required.
2. Open Console, type only one of the following commands and press return. This may ask for your password but not show you typing it.

sudo pacman -S ollama-rocm    # for AMD GPU
sudo pacman -S ollama-cuda    # for NVIDIA GPU
sudo pacman -S ollama         # for no GPU (for CPU)

3. Enable the Ollama service [on-device and runs in the background] to start with your device and start it now.

sudo systemctl enable --now ollama

Test Ollama alone (Open WebUI guide coming soon)

1. Open localhost:11434 in a web browser and you should see Ollama is running. This shows Ollama is installed and its service is running.
2. Run ollama run deepseek-r1 in a console and ollama ps in another, to download and run the DeepSeek R1 model while seeing whether Ollama is using your slow CPU or fast GPU.

AMD GPU issue fix

https://lemmy.world/post/27088416

cross-posted from: https://lemmy.world/post/27013201

Ollama lets you download and run large language models (LLMs) on your device.

Install Ollama on Arch Linux (Windows guide coming soon)

1. Check whether your device has an AMD GPU, NVIDIA GPU, or no GPU. A GPU is recommended but not required.
2. Open Console, type only one of the following commands and press return. This may ask for your password but not show you typing it.

sudo pacman -S ollama-rocm    # for AMD GPU
sudo pacman -S ollama-cuda    # for NVIDIA GPU
sudo pacman -S ollama         # for no GPU (for CPU)

3. Enable the Ollama service [on-device and runs in the background] to start with your device and start it now.

sudo systemctl enable --now ollama

Test Ollama alone (Open WebUI guide coming soon)

1. Open localhost:11434 in a web browser and you should see Ollama is running. This shows Ollama is installed and its service is running.
2. Run ollama run deepseek-r1 in a console and ollama ps in another, to download and run the DeepSeek R1 model while seeing whether Ollama is using your slow CPU or fast GPU.

AMD GPU issue fix

https://lemmy.world/post/27088416

Ollama lets you download and run large language models (LLMs) on your device.

Install Ollama on Arch Linux (Windows guide coming soon)

1. Check whether your device has an AMD GPU, NVIDIA GPU, or no GPU. A GPU is recommended but not required.
2. Open Console, type only one of the following commands and press return. This may ask for your password but not show you typing it.

sudo pacman -S ollama-rocm    # for AMD GPU
sudo pacman -S ollama-cuda    # for NVIDIA GPU
sudo pacman -S ollama         # for no GPU (for CPU)

3. Enable the Ollama service [on-device and runs in the background] to start with your device and start it now.

sudo systemctl enable --now ollama

Test Ollama alone (Open WebUI guide coming soon)

1. Open localhost:11434 in a web browser and you should see Ollama is running. This shows Ollama is installed and its service is running.
2. Run ollama run deepseek-r1 in a console and ollama ps in another, to download and run the DeepSeek R1 model while seeing whether Ollama is using your slow CPU or fast GPU.

AMD GPU issue fix

https://lemmy.world/post/27088416

cross-posted from: https://lemmy.world/post/27009486

!llm@lemmy.world community and @zazule@lemmy.world moderator appear inactive.

watomatic.app

Example

🤖 Automated Reply

💬 I reply faster on example.org

⁉️ WhatsApp is anti-libre software. We do NOT control it. It withholds a libre software license text file, like GPL.

Explained

I reply faster on

Deleting the only way to reach someone online breaks your influence.

example.org

A link and only one link, so (1) they see it's an app, not some random word or typo, (2) they can download it without searching, and (3) they don't have multiple choice–they don't need to do any thinking or research. Remove everything stopping them.

anti-libre software.

Never say privacy, they've heard it all before (from you, no doubt). Say something different.

We do NOT control it.

Make it simple and direct. Think of the most removed person you know and break it down in a way they would understand. Think about every angle it could be misunderstood.

It withholds

Libre software is normal, default. Anti-libre software is cringe, weird, dangerous. Act like it. Also, humans care less about getting and more about losing stuff.

libre software license text file

Show them what to check for, for themselves, easily, obvious. Later, show them how to spread these ideas. Then, show them how to show others how to spread these ideas, make more of you.

GPL

A keyword for them to web search for more, with better results than more complex terms like AGPL or misleading terms like 'open source'.

Don't waste a word.

Lastly, make yourself someone everyone wants to talk to.

Automatic calendar synchronisation with no server and no cloud?