feat: bump transformers to allow Qwen3-VL (#225)

remove unsupported cuda versions (12.1-12.3) from hub.json and tests.json
to fix compatibility issues with worker deployment

- hub.json: remove 12.1, 12.2, 12.3 from allowedCudaVersions
- tests.json: remove 12.1, 12.2, 12.3, 12.4 from allowedCudaVersions

refs: AE-1452

.runpod/hub.json

@@ -6,20 +6,10 @@
   "iconUrl": "https://registry.npmmirror.com/@lobehub/icons-static-png/latest/files/dark/vllm-color.png",
   "config": {
     "runsOn": "GPU",
-    "containerDiskInGb": 200,
+    "containerDiskInGb": 150,
     "gpuIds": "ADA_80_PRO,AMPERE_80",
     "gpuCount": 1,
-    "allowedCudaVersions": [
-      "12.9",
-      "12.8",
-      "12.7",
-      "12.6",
-      "12.5",
-      "12.4",
-      "12.3",
-      "12.2",
-      "12.1"
-    ],
+    "allowedCudaVersions": ["12.9", "12.8", "12.7", "12.6", "12.5", "12.4"],
     "presets": [
       {
         "name": "deepseek-ai/deepseek-r1-distill-llama-8b",

.runpod/tests.json

@@ -38,14 +38,6 @@
         "value": "HuggingFaceTB/SmolLM2-135M-Instruct"
       }
     ],
-    "allowedCudaVersions": [
-      "12.7",
-      "12.6",
-      "12.5",
-      "12.4",
-      "12.3",
-      "12.2",
-      "12.1"
-    ]
+    "allowedCudaVersions": ["12.9", "12.8", "12.7", "12.6", "12.5"]
   }
 }

builder/requirements.txt

@@ -8,7 +8,7 @@ typing-extensions>=4.8.0
 pydantic
 pydantic-settings
 hf-transfer
-transformers>=4.55.0
+transformers>=4.57.0
 bitsandbytes>=0.45.0
 kernels
 torch==2.6.0