Files
worker-vllm/.runpod/tests.json
T
Tim PietruskyandGitHub 6337a6673a
Release / release (push) Waiting to run
fix: allow also CUDA 12.8 & 12.9 (#228)
2025-10-24 18:48:26 +02:00

54 lines
1.1 KiB
JSON

{
"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": {
"messages": [
{
"role": "system",
"content": "You are a helpful assistant that writes concise responses."
},
{
"role": "user",
"content": "Explain what a neural network is in one sentence."
}
],
"max_tokens": 200,
"temperature": 0.1
}
},
"timeout": 30000
}
],
"config": {
"gpuTypeId": "NVIDIA GeForce RTX 4090",
"gpuCount": 1,
"env": [
{
"key": "MODEL_NAME",
"value": "HuggingFaceTB/SmolLM2-135M-Instruct"
}
],
"allowedCudaVersions": [
"12.9",
"12.8",
"12.7",
"12.6",
"12.5",
"12.4",
"12.3",
"12.2",
"12.1"
]
}
}