1AndOnlyPika Posts - Answer Overflow

1AndOnlyPika

•Created by 1AndOnlyPika on 10/8/2024 in #⚡｜serverless

New release on frontend changes ALL endpoints

When I publish a new release to one endpoint through the runpod website, I noticed that it will push the release to all other endpoints as well. This has messed up a few of my workflows.

3 replies

RRunPod

•Created by 1AndOnlyPika on 10/6/2024 in #⚡｜serverless

Reporting/blacklisting poorly performing workers

I've noticed that every now and then a bad worker is spawned for my endpoint which takes forever to complete the job when compared to other workers running the same job. Typically my job would take ~40s but there are occassionally workers that have the same gpu but take 70s instead. I want to blacklist these pods from running my endpoint so performance isnt impacted

24 replies

RRunPod

•Created by 1AndOnlyPika on 10/5/2024 in #⚡｜serverless

Flashboot not working

56 replies

RRunPod

•Created by 1AndOnlyPika on 9/12/2024 in #⚡｜serverless

One request = one worker

How can I configure my endpoint so that one request is equal to one worker, and one worker does not complete more than one request within a certain timeframe? My workload is bursty and requires all of the workers to be available at once. However, my endpoint does not give that and takes a long time to start all the workers I need. In addition, workers are sometimes reused instead of creating a new instance which I do not want.

71 replies

RRunPod

•Created by 1AndOnlyPika on 8/22/2024 in #⛅｜pods

Persistent container disk

Is there a way to make the container disk mounted at / persistent for a pod instead of the additional drive at /workspace or whatever?

6 replies

RRunPod

•Created by 1AndOnlyPika on 8/19/2024 in #⛅｜pods

Resuming an on demand pod via sdk

Hello, how can I resume a spot pod through the python sdk? I am using the resume_pod function but I am not able to

3 replies

RRunPod