feat: prepare worker-vllm for the hub (#214)

* docs: remove outdated video; remove old info; added missing config for tools

* ci: use proper release for dev (pr only) and production (release only)

* ci(hub): added openai example; use smollm2 as base model

* docs: added conventions to be able to work with ai ide's

* chore: remove outdated stuff

* chore: update copyright to 2025

* ci: added github permissions

* feat: added gpuIds, gputCount and allowedCudaVersions; removed default value for LOAD_FORMAT to check which influence this has on the ui

---------

Co-authored-by: Tim Pietrusky <tim.pietrusky@runpod.io>

.runpod/hub.json

@@ -7,6 +7,19 @@
   "config": {
     "runsOn": "GPU",
     "containerDiskInGb": 200,
+    "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"
+    ],
     "presets": [
       {
         "name": "deepseek-ai/deepseek-r1-distill-llama-8b",
@@ -129,7 +142,6 @@
               "value": "bitsandbytes"
             }
           ],
-          "default": "auto",
           "advanced": true
         }
       },

.runpod/tests.json

@@ -1,32 +1,52 @@
 {
-    "tests": [
-        {
-            "name": "basic_inference_test",
-            "input": {
-                "prompt": "Write a short poem about artificial intelligence."
-            },
-            "timeout": 30000
-        }
-    ],
-    "config": {
-        "gpuTypeId": "NVIDIA GeForce RTX 4090",
-        "gpuCount": 1,
-        "env": [
+  "tests": [
+    {
+      "name": "basic_inference_test",
+      "input": {
+        "prompt": "Write a short poem about artificial intelligence."
+      },
+      "timeout": 30000
+    },
+    {
+      "name": "openai_messages_test",
+      "input": {
+        "openai_route": "/v1/chat/completions",
+        "openai_input": {
+          "model": "HuggingFaceTB/SmolLM2-135M-Instruct",
+          "messages": [
             {
-                "key": "MODEL_NAME",
-                "value": "facebook/opt-350m"
+              "role": "system",
+              "content": "You are a helpful assistant that writes concise responses."
+            },
+            {
+              "role": "user",
+              "content": "Explain what a neural network is in one sentence."
             }
-        ],
-        "allowedCudaVersions": [
-            "12.7",
-            "12.6",
-            "12.5",
-            "12.4",
-            "12.3",
-            "12.2",
-            "12.1",
-            "12.0",
-            "11.7"
-        ]
+          ],
+          "max_tokens": 50,
+          "temperature": 0.7
+        }
+      },
+      "timeout": 30000
     }
+  ],
+  "config": {
+    "gpuTypeId": "NVIDIA GeForce RTX 4090",
+    "gpuCount": 1,
+    "env": [
+      {
+        "key": "MODEL_NAME",
+        "value": "HuggingFaceTB/SmolLM2-135M-Instruct"
+      }
+    ],
+    "allowedCudaVersions": [
+      "12.7",
+      "12.6",
+      "12.5",
+      "12.4",
+      "12.3",
+      "12.2",
+      "12.1"
+    ]
+  }
 }