Angel
RRunPod
•Created by Angel on 9/10/2024 in #⚡｜serverless
Creating endpoint through runpodclt
Hello there. I am trying to test and deploy a basic serverless endpoint. Issues that I have and don't understand:
- If I create a serverless endpoint through the web, then I don't need to select a network volume. In this case I think I am forced to use Docker.
- Because I don't want to explicitly use docker, iam using runpodclt as described:
https://blog.runpod.io/runpod-dockerless-cli-innovation/
I created a new project with:
gpu_types = [
"NVIDIA GeForce RTX 4080", # 16GB
"NVIDIA RTX A4000",
"NVIDIA RTX A4500", # 16GB
"NVIDIA RTX A4500 Ada", # 16GB
"NVIDIA RTX A5000", # 24GB
]
I created a new network volume in the CA-MTL-1 region, which, according to the web page has a high A5000 availability.
But when I call runpodctl project dev I get:
name = "test-project"
[endpoint]
active_workers = 0
flashboot = true
max_workers = 3
[project]
base_image = "runpod/base:0.6.1-cuda11.8.0"
container_disk_size_gb = 30
gpu_count = 1
gpu_types = ["NVIDIA GeForce RTX 4080", "NVIDIA RTX A4000", "NVIDIA RTX A4500", "NVIDIA RTX A4500 Ada", "NVIDIA RTX A5000"]
ports = "4040/http, 7270/http, 22/tcp"
uuid = "8777bf75"
volume_mount_path = "/runpod-volume"
[project.env_vars]
POD_INACTIVITY_TIMEOUT = "120"
RUNPOD_DEBUG_LEVEL = "debug"
UVICORN_LOG_LEVEL = "warning"
[runtime]
handler_path = "src/handler.py"
python_version = "3.10"
requirements_path = "builder/requirements.txt"
Deploying project Pod on RunPod...
Trying to get a Pod with NVIDIA GeForce RTX 4080... Unavailable.
Trying to get a Pod with NVIDIA RTX A4000... Unavailable.
Trying to get a Pod with NVIDIA RTX A4500... Unavailable.
Trying to get a Pod with NVIDIA RTX A4500 Ada... Unavailable.
Trying to get a Pod with NVIDIA RTX A5000... Unavailable.
none of the selected GPU types were available
Can you help me?
It is possible to avoid having to select a region when creating a network volume? Thans
6 replies
