Runpod

R

Runpod

We're a community of enthusiasts, engineers, and enterprises, all sharing insights on AI, Machine Learning and GPUs!

Join

⚡|serverless

⛅|pods

🔧|api-opensource

📡|instant-clusters

🗂|hub

Issue with worker-vllm and multiple workers

I'm using the previous version of the worker-vllm (https://github.com/runpod-workers/worker-vllm/tree/4f792062aaea02c526ee906979925b447811ef48). There is an issue when more than 1 workers are running. Since vLLM has internal queue, all the requests are being immediately passed to the one worker. The second worker doesn't receive any requests. It it possible to solve it? I've tried a new version of the worker-vllm but there are some other issues. Thanks!

Throttled

Hey 🙂 Is there something I can do to prevent getting throttled? I see the availability for the GPU I selected is high, and I'm also not using any network disk, so I'm a bit confused what's exactly happening. ID: ofjdhe4djh1k5t...

Cuda Version in serverless

Which cuda version is being used in A100 80 gb gpu at serverless ?

4minute Serverless (Server Not Ready) Constantly.

Sometimes getting a serverless worker boot up, run for ~5mins with "2023-12-18T16:18:12.087432983Z {"requestId": null, "message": "Service not ready yet. Retrying...", "level": "INFO"}" constantly repeating. Then does nothing and deletes.

Can worker-vllm work with https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ

I have customers that want to use this and I think worker-vllm is the way to go with it. Hope it can work with worker-vllm! Link is https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ and I guess it works with text-generation-webui so why not worker-vllm

Unable to access network volume data from serverless deployment

I have a network volume called models (id: 07k4ohphfw) I deployed a Pod (id: t4piur6ezzwjrn) to populate this network volume with models in the /workspace directory. I created multiple serverless endpoints to try and access the models in my network volume. I created have a serverless endpoint (id: k0xfhgd47d2xk8) for debugging purposes, which simply lists the files in /runpod-volume. The volume is attached to the serverless endpoint. However, runpod-volume is completely empty when I try to access it. ...

Stop button missing

Can’t find Stop button in my pod ID 8uiw7twm1deb2y Only option is to terminate pod...
No description

Not able to run Jupyter Lab?

Not other pods are running - no idea why I cannot run Jupyter Lab on port 8888 when it worked just fine the previous evening. #⚡|serverless runpod
No description

Running Spaces on Runpod Error

Following the Docker to Runpod Instruct I get the following error:
No description

Fooocus run_anime.bat

Hi, i try fooocus community template today on my pods. But i want to try to run anime presets of fooocus. How i can do that?
No description