Ollama-integraatio: GPU-inferenssi NVIDIA/AMD/Apple, ei Candle-rajoitteita

- docker-compose: Ollama-container GPU:lla + persistent volume malleille
- native-node: Candle poistettu, kutsuu Ollaman HTTP API:a (async)
- Dockerfile: yksinkertaistettu, ei CUDA SDK:ta (Ollama hoitaa GPU:n)
- Tukee kaikkia malleja: qwen2.5-coder:1.5b/3b/7b/14b/32b
- OLLAMA_MODEL ympäristömuuttujalla vaihdetaan malli
- kpn models näyttää Ollama-mallit nopeustiedoilla

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

network-poc/Dockerfile.native-node

@@ -1,13 +1,9 @@
-FROM nvidia/cuda:12.6.3-devel-ubuntu24.04 AS builder
+FROM rust:slim AS builder
 
 RUN apt-get update && apt-get install -y \
-    curl pkg-config libssl-dev g++ libvulkan-dev \
+    pkg-config libssl-dev g++ libvulkan-dev \
     && rm -rf /var/lib/apt/lists/*
 
-# Rust
-RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
-ENV PATH="/root/.cargo/bin:${PATH}"
-
 WORKDIR /app
 COPY Cargo.toml Cargo.lock ./
 COPY hub/Cargo.toml hub/Cargo.toml
@@ -24,15 +20,15 @@ RUN mkdir -p hub/src node/src native-node/src cli/src \
     && cargo build --release -p native-node 2>/dev/null || true
 
 COPY native-node/src native-node/src
-# RTX 4090 = sm_89, RTX 3090 = sm_86, RTX 2080 = sm_75
-ENV CUDA_COMPUTE_CAP=89
 RUN cargo build --release -p native-node
 
-FROM nvidia/cuda:12.6.3-runtime-ubuntu24.04
+FROM debian:bookworm-slim
 RUN apt-get update && apt-get install -y ca-certificates libvulkan1 && rm -rf /var/lib/apt/lists/*
 COPY --from=builder /app/target/release/native-node /usr/local/bin/native-node
 
 ENV HUB_URL=ws://agentic-poc:3000/ws
+ENV OLLAMA_URL=http://ollama:11434
+ENV OLLAMA_MODEL=qwen2.5-coder:7b
 ENV ALLOCATED_GB=4
 
 CMD ["native-node"]