From 8bab07201a177cb6123df815f8c2385826c8b109 Mon Sep 17 00:00:00 2001 From: chemavx Date: Fri, 24 Apr 2026 15:34:37 +0000 Subject: [PATCH] ollama: elimina GPU, fija imagen 0.20.7, reduce a qwen2.5:3b MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Imagen: ollama/ollama:latest → ollama/ollama:0.20.7 - Elimina NVIDIA_VISIBLE_DEVICES, NVIDIA_DRIVER_CAPABILITIES - Elimina nvidia.com/gpu: "1" de resources limits - Reduce memory: 8/20Gi → 4/8Gi (solo CPU, modelo 3b) - Startup: auto-pull cambiado a qwen2.5:3b Co-Authored-By: Claude Sonnet 4.6 --- ollama/ollama.yaml | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/ollama/ollama.yaml b/ollama/ollama.yaml index 095dcc9..a875106 100644 --- a/ollama/ollama.yaml +++ b/ollama/ollama.yaml @@ -42,7 +42,7 @@ spec: kubernetes.io/hostname: chemavx-k8 containers: - name: ollama - image: ollama/ollama:latest + image: ollama/ollama:0.20.7 command: ["/usr/bin/bash", "-c"] args: - | @@ -53,8 +53,7 @@ spec: sleep 2 done echo "Pulling llama3.1:8b..." - ollama pull llama3.1:8b - ollama rm llama3.2:3b 2>/dev/null || true + ollama pull qwen2.5:3b echo "Model ready." wait $SERVE_PID ports: @@ -68,17 +67,12 @@ spec: value: "8192" - name: OLLAMA_KEEP_ALIVE value: "-1" - - name: NVIDIA_VISIBLE_DEVICES - value: all - - name: NVIDIA_DRIVER_CAPABILITIES - value: compute,utility resources: requests: - memory: 8Gi + memory: 4Gi cpu: "500m" limits: - memory: 20Gi - nvidia.com/gpu: "1" + memory: 8Gi volumeMounts: - name: ollama-data mountPath: /root/.ollama