R
RunPod•3mo ago
rcmalli

No GPU Available

Hello, I have using the 'runpodctl' workflow with dev and deploy commands and I have one network volume attached in EU-RO-1 zone. Currently whenever I run 'runpodctl project dev', CLI says that there are no GPUs available. Is it true or actually no GPU is left? Here is the part related inside my 'runpod.toml' file: base_image = "runpod/base:0.6.1-cuda12.2.0" gpu_types = [ "NVIDIA GeForce RTX 4080", # 16GB "NVIDIA RTX A4000", # 16GB "NVIDIA RTX A4500", # 20GB "NVIDIA RTX A5000", # 24GB "NVIDIA GeForce RTX 3090", # 24GB "NVIDIA GeForce RTX 4090", # 24GB "NVIDIA RTX A6000", # 48GB "NVIDIA A100 80GB PCIe", # 80GB ] gpu_count = 1 volume_mount_path = "/runpod-volume" ports = "4040/http, 7270/http, 22/tcp" # FileBrowser, FastAPI, SSH container_disk_size_gb = 100
3 Replies
ashleyk
ashleyk•3mo ago
4090, A4500, and 4000 Ada are available, so not sure why it says none are available. I see 4000 Ada isn't in your list though.
rcmalli
rcmalli•3mo ago
I have added more but it is same
No description
rcmalli
rcmalli•3mo ago
I am using 'runpodctl' version 1.14.2. Is something changed related to gpu type definitions recently?
Want results from more Discord servers?
Add your server
More Posts
Find Config of Deleted PodIs there any way to view the *config* of a pod that was already deleted? I see the pod creation lisHow to load model into memory before the first run of a pod?In the template worker, in the handler file it is written: ```py # If your handler runs inference onIncrease number workersI have at the moment a number of workers of 10. How can I increase the maximum number of them ?High execution time, high amount of failed jobs36% of my serverless jobs have failed this morning and the execution time has spiked massively. ThiHow do I write handler for /runWhen I create a handler `runpod.serverless.start({"handler": async_generator_handler})` Only http://How do indicated job status in a handler?For example in https://docs.runpod.io/serverless/workers/handlers/handler-async ``` import runpod imA6000 serverless worker is failing for an unknown reason.In the last week a few of our serverless workers have been failing on all requests. Trying to narrowCan multiple models be queried using the vllm serverless worker?Just getting started with the vllm serverless worker and my first question is can I query multiple mDidn't get response via email, trying my luck hereHi, we've reached out to you via email to maybe setup a meet and didn't get a response. We need yourtorch.cuda.is_available() is FalseSpinning up several H100s (burning money 😅) and no matter which official docker image I use, `torch