update ai stack with turbo

active/software_ai_stack/llama-instruct.container

@@ -21,17 +21,17 @@ Exec=--port 8002 \
     -n 32768 \
     --temp 0.7 \
     --top-p 0.8 \
-    --min-p 0.0 \
     --top-k 20 \
-    --repeat-penalty 1.0 \
     --presence-penalty 1.5 \
-    --reasoning-budget 0 \
+    --min-p 0.00 \
     --perf \
     --n-gpu-layers all \
+    -fa on \
+    --spec-type draft-mtp --spec-draft-n-max 2 \
     --jinja \
-    -m /models/qwen3.6-35b-a3b/Qwen3.6-35B-A3B-UD-Q5_K_M.gguf \
-    --mmproj /models/qwen3.6-35b-a3b/mmproj-F16.gguf \
-    --chat-template-kwargs '{"enable_thinking": false}' \
+    --chat-template-kwargs '{"preserve_thinking": false, "enable_thinking": false}' \
+    -m /models/qwen3.6-35b-a3b-mtp/Qwen3.6-35B-A3B-UD-Q5_K_M.gguf \
+    --mmproj /models/qwen3.6-35b-a3b-mtp/mmproj-F16.gguf \
     --alias instruct
 
 # Health Check
@@ -41,7 +41,8 @@ HealthRetries=3
 HealthStartPeriod=10s
 HealthTimeout=30s
 HealthOnFailure=kill
-EnvironmentFile=/home/ai/.llama-api/keys.env
+
+# EnvironmentFile=/home/ai/.llama-api/keys.env
 
 [Service]
 Restart=always