Update renovate/renovate Docker tag to v43.59.2

apps/llama/configs/config.yaml

@@ -461,6 +461,7 @@ models:
       /app/llama-server
         -hf unsloth/Qwen3-Coder-Next-GGUF:Q4_K_M
         --ctx-size 32768
+        --fit-target 2048
         --predict 8192
         --temp 1.0
         --min-p 0.01
@@ -475,6 +476,7 @@ models:
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M
+        --fit-target 2048
         --ctx-size 16384
         --temp 1.0
         --min-p 0.00
@@ -488,6 +490,7 @@ models:
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M
+        --fit-target 2048
         --ctx-size 16384
         --temp 1.0
         --min-p 0.00
@@ -506,6 +509,7 @@ models:
         -hf mradermacher/Qwen3.5-35B-A3B-heretic-GGUF:Q4_K_M
         --mmproj-url https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF/resolve/main/mmproj-F16.gguf
         --mmproj /root/.cache/llama.cpp/unsloth_Qwen3.5-35B-A3B-GGUF_mmproj-F16.gguf
+        --fit-target 2048
         --ctx-size 16384
         --temp 1.0
         --min-p 0.00
@@ -521,6 +525,7 @@ models:
         -hf mradermacher/Qwen3.5-35B-A3B-heretic-GGUF:Q4_K_M
         --mmproj-url https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF/resolve/main/mmproj-F16.gguf
         --mmproj /root/.cache/llama.cpp/unsloth_Qwen3.5-35B-A3B-GGUF_mmproj-F16.gguf
+        --fit-target 2048
         --ctx-size 16384
         --temp 1.0
         --min-p 0.00
@@ -561,6 +566,20 @@ models:
         --no-warmup
         --port ${PORT}
 
+  "Qwen3.5-0.8B-GGUF:Q4_K_XL":
+    ttl: 0
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-0.8B-GGUF:Q4_K_XL
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+        --chat-template-kwargs "{\"enable_thinking\": true}"
+
   "Qwen3.5-0.8B-GGUF-nothink:Q4_K_XL":
     ttl: 0
     cmd: |
@@ -574,3 +593,115 @@ models:
         --no-warmup
         --port ${PORT}
         --chat-template-kwargs "{\"enable_thinking\": false}"
+
+  "Qwen3.5-2B-GGUF:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-2B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+        --chat-template-kwargs "{\"enable_thinking\": true}"
+
+  "Qwen3.5-2B-GGUF-nothink:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-2B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+        --chat-template-kwargs "{\"enable_thinking\": false}"
+
+  "Qwen3.5-4B-GGUF:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-4B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+        --chat-template-kwargs "{\"enable_thinking\": true}"
+
+  "Qwen3.5-4B-GGUF-nothink:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-4B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+        --chat-template-kwargs "{\"enable_thinking\": false}"
+
+  "Qwen3.5-9B-GGUF:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-9B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+        --chat-template-kwargs "{\"enable_thinking\": true}"
+
+  "Qwen3.5-9B-GGUF-nothink:Q4_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-9B-GGUF:Q4_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+        --chat-template-kwargs "{\"enable_thinking\": false}"
+
+  "Qwen3.5-9B-GGUF:Q3_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-9B-GGUF:Q3_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+        --chat-template-kwargs "{\"enable_thinking\": true}"
+
+  "Qwen3.5-9B-GGUF-nothink:Q3_K_M":
+    ttl: 600
+    cmd: |
+      /app/llama-server
+        -hf unsloth/Qwen3.5-9B-GGUF:Q3_K_M
+        --ctx-size 16384
+        --temp 0.6
+        --top-p 0.95
+        --top-k 20
+        --min-p 0.00
+        --no-warmup
+        --port ${PORT}
+        --chat-template-kwargs "{\"enable_thinking\": false}"

apps/llama/deployment.yaml

@@ -6,6 +6,8 @@ metadata:
   namespace: llama
 spec:
   replicas: 1
+  strategy:
+    type: Recreate
   selector:
     matchLabels:
       app: llama-swap

apps/renovate/cronjob.yaml

@@ -15,7 +15,7 @@ spec:
             - name: renovate
               # Update this to the latest available and then enable Renovate on
               # the manifest
-              image: renovate/renovate:43.56.1-full
+              image: renovate/renovate:43.59.2-full
               envFrom:
                 - secretRef:
                     name: renovate-gitea-token