Merge branch 'nrvo-ollama-amd'

apps/ollama-amd/config.json

@@ -0,0 +1,18 @@
+{
+  "$schema": "../schema.json",
+  "name": "Ollama - AMD",
+  "available": true,
+  "exposable": true,
+  "port": 11434,
+  "id": "ollama-amd",
+  "tipi_version": 1,
+  "version": "0.1.33",
+  "categories": ["ai"],
+  "description": "Get up and running with Llama 3, Mistral, Gemma, and other large language models.",
+  "short_desc": "LLMs inference server with OpenAI compatible API",
+  "author": "ollama",
+  "source": "https://github.com/ollama/ollama",
+  "website": "https://ollama.com",
+  "form_fields": [],
+  "supported_architectures": ["arm64", "amd64"]
+}

apps/ollama-amd/docker-compose.yml

@@ -0,0 +1,44 @@
+version: '3.7'
+
+services:
+  ollama-amd:
+    image: ollama/ollama:0.1.33-rocm
+    restart: unless-stopped
+    container_name: ollama-amd
+    environment:
+      - PORT=11434
+    ports:
+      - '${APP_PORT}:11434'
+    networks:
+      - tipi_main_network
+    volumes:
+      - ${APP_DATA_DIR}/data/.ollama:/root/.ollama
+    devices:
+      # Attach GPU
+      - /dev/kfd
+      - /dev/dri
+    labels:
+      # Main
+      traefik.enable: true
+      traefik.http.middlewares.ollama-amd-web-redirect.redirectscheme.scheme: https
+      traefik.http.services.ollama-amd.loadbalancer.server.port: 11434
+      # Web
+      traefik.http.routers.ollama-amd-insecure.rule: Host(`${APP_DOMAIN}`)
+      traefik.http.routers.ollama-amd-insecure.entrypoints: web
+      traefik.http.routers.ollama-amd-insecure.service: ollama-amd
+      traefik.http.routers.ollama-amd-insecure.middlewares: ollama-amd-web-redirect
+      # Websecure
+      traefik.http.routers.ollama-amd.rule: Host(`${APP_DOMAIN}`)
+      traefik.http.routers.ollama-amd.entrypoints: websecure
+      traefik.http.routers.ollama-amd.service: ollama-amd
+      traefik.http.routers.ollama-amd.tls.certresolver: myresolver
+      # Local domain
+      traefik.http.routers.ollama-amd-local-insecure.rule: Host(`ollama-amd.${LOCAL_DOMAIN}`)
+      traefik.http.routers.ollama-amd-local-insecure.entrypoints: web
+      traefik.http.routers.ollama-amd-local-insecure.service: ollama-amd
+      traefik.http.routers.ollama-amd-local-insecure.middlewares: ollama-amd-web-redirect
+      # Local domain secure
+      traefik.http.routers.ollama-amd-local.rule: Host(`ollama-amd.${LOCAL_DOMAIN}`)
+      traefik.http.routers.ollama-amd-local.entrypoints: websecure
+      traefik.http.routers.ollama-amd-local.service: ollama-amd
+      traefik.http.routers.ollama-amd-local.tls: true

apps/ollama-amd/metadata/description.md

@@ -0,0 +1,72 @@
+## Usage
+
+⚠️ This app runs on port **11434**. Take this into account when configuring tools connecting to the app.
+
+### Use with a frontend
+
+- [LobeChat](https://github.com/lobehub/lobe-chat)
+- [LibreChat](https://github.com/danny-avila/LibreChat)
+- [OpenWebUI](https://github.com/open-webui/open-webui)
+- [And more ...](https://github.com/ollama/ollama)
+
+---
+
+### Try the REST API
+
+Ollama has a REST API for running and managing models.
+
+**Generate a response**
+
+```sh
+curl http://localhost:11434/api/generate -d '{
+  "model": "llama3",
+  "prompt":"Why is the sky blue?"
+}'
+```
+
+**Chat with a model**
+
+```sh
+curl http://localhost:11434/api/chat -d '{
+  "model": "llama3",
+  "messages": [
+    { "role": "user", "content": "why is the sky blue?" }
+  ]
+}'
+```
+
+---
+
+## Compatible GPUs
+
+Ollama supports the following AMD GPUs:
+| Family | Cards and accelerators |
+| -------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- |
+| AMD Radeon RX | `7900 XTX` `7900 XT` `7900 GRE` `7800 XT` `7700 XT` `7600 XT` `7600` `6950 XT` `6900 XTX` `6900XT` `6800 XT` `6800` `Vega 64` `Vega 56` |
+| AMD Radeon PRO | `W7900` `W7800` `W7700` `W7600` `W7500` `W6900X` `W6800X Duo` `W6800X` `W6800` `V620` `V420` `V340` `V320` `Vega II Duo` `Vega II` `VII` `SSG` |
+| AMD Instinct | `MI300X` `MI300A` `MI300` `MI250X` `MI250` `MI210` `MI200` `MI100` `MI60` `MI50` |
+
+---
+
+## Model library
+
+Ollama supports a list of models available on [ollama.com/library](https://ollama.com/library 'ollama model library')
+
+Here are some example models that can be downloaded:
+
+| Model              | Parameters | Size  | Download                       |
+| ------------------ | ---------- | ----- | ------------------------------ |
+| Llama 3            | 8B         | 4.7GB | `ollama run llama3`            |
+| Llama 3            | 70B        | 40GB  | `ollama run llama3:70b`        |
+| Phi-3              | 3,8B       | 2.3GB | `ollama run phi3`              |
+| Mistral            | 7B         | 4.1GB | `ollama run mistral`           |
+| Neural Chat        | 7B         | 4.1GB | `ollama run neural-chat`       |
+| Starling           | 7B         | 4.1GB | `ollama run starling-lm`       |
+| Code Llama         | 7B         | 3.8GB | `ollama run codellama`         |
+| Llama 2 Uncensored | 7B         | 3.8GB | `ollama run llama2-uncensored` |
+| LLaVA              | 7B         | 4.5GB | `ollama run llava`             |
+| Gemma              | 2B         | 1.4GB | `ollama run gemma:2b`          |
+| Gemma              | 7B         | 4.8GB | `ollama run gemma:7b`          |
+| Solar              | 10.7B      | 6.1GB | `ollama run solar`             |
+
+> Note: You should have at least 8 GB of RAM available to run the 7B models, 16 GB to run the 13B models, and 32 GB to run the 33B models.