30 lines
780 B
JSON
30 lines
780 B
JSON
{
|
|
"title": "vLLM",
|
|
"description": "Deploy OpenAI-Compatible Blazing-Fast LLM Endpoints powered by the vLLM Inference Engine on RunPod Serverless",
|
|
"type": "serverless",
|
|
"category": "language",
|
|
"iconUrl": "https://registry.npmmirror.com/@lobehub/icons-static-png/latest/files/dark/vllm-color.png",
|
|
"config": {
|
|
"runsOn": "GPU",
|
|
"containerDiskInGb": 200,
|
|
"presets": [
|
|
{
|
|
"name": "deepseek-ai/deepseek-r1-distill-llama-8b",
|
|
"defaults": {
|
|
"MODEL_NAME": "deepseek-ai/deepseek-r1-distill-llama-8b"
|
|
}
|
|
}
|
|
],
|
|
"env": [
|
|
{
|
|
"key": "MODEL_NAME",
|
|
"input": {
|
|
"name": "Model Name",
|
|
"type": "huggingface",
|
|
"default": "openai-community/gpt2"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
}
|