monitoring: llama-swap GPU/LLM stack (v250) — PrometheusRule, Grafana dashboard, scrape config, VRAM exporter

ansible/roles/llm-inference-multimodel/templates/llama-swap-config.yaml.j2

@@ -0,0 +1,59 @@
+{# 
+  FILE: roles/llm-inference-multimodel/templates/llama-swap-config.yaml.j2
+  DESCRIPTION: llama-swap v250 configuration template.
+               Generates /etc/llama-swap/config.yaml with all models, routing matrix,
+               and per-model settings (ctx_size, n_gpu_layers, cmd args).
+  
+  v250 SYNTAX NOTES:
+  - Uses routing.router DSL with expression-based matrix (not old list-of-arrays)
+  - Each model has its own cmd field with full per-model args
+  - Matrix rows use "model1 & model2" syntax for co-resident sets
+  - sleep_idle_seconds: -1 = never idle; 0+ = idle after N seconds
+  - load_on_startup: true = start this model on service startup
+  
+  Reference: /etc/llama-swap/config.yaml on astro-orbiter (Phase 1 artifact)
+#}
+# llama-swap configuration for astro-orbiter
+# Generated by Ansible roles/llm-inference-multimodel on {{ ansible_date_time.iso8601 }}
+# See: https://github.com/mostlygeek/llama-swap (v250 release notes for syntax)
+
+# ============================================================================
+# LISTEN — Address and port for the llama-swap proxy
+# ============================================================================
+listen: "{{ llm_swapmode_bind_address }}:{{ llm_swapmode_port }}"
+
+# ============================================================================
+# MODELS — All model definitions (cmd, port, ctx_size, etc.)
+# ============================================================================
+models:
+{% for model in llm_swapmode_models %}
+  {{ model.id }}:
+    cmd: >
+      llama-server
+      --port ${PORT}
+      --model {{ model.gguf_path }}
+      --n-gpu-layers {{ model.n_gpu_layers }}
+      --ctx-size {{ model.ctx_size }}
+      --batch-size {{ model.batch_size }}
+      --ubatch-size {{ model.ubatch_size }}
+      --parallel {{ model.parallel }}
+      {% if model.cache_type is defined %}--cache-type-k {{ model.cache_type }} --cache-type-v {{ model.cache_type }}{% endif %}
+      {% if model.flash_attn is defined %}--flash-attn {{ model.flash_attn }}{% endif %}
+      {% if model.sleep_idle_seconds is defined %}--sleep-idle-seconds {{ model.sleep_idle_seconds }}{% endif %}
+      {% if model.load_on_startup is defined and model.load_on_startup %}--load-on-startup{% endif %}
+      --host 127.0.0.1
+    port: {{ model.port }}
+{% endfor %}
+
+# ============================================================================
+# ROUTING — Matrix-based hot-swap policy (v250 expression DSL)
+# ============================================================================
+routing:
+  router:
+    use: matrix
+    settings:
+      matrix:
+        sets:
+{% for row in llm_swapmode_matrix_rows %}
+          {{ row.row }}: "{{ row.expr }}"
+{% endfor %}