heyado
RRunPod
•Created by heyado on 8/16/2024 in #⚡｜serverless
Best tips for lowering SDXL text2image API startup latency?
I'm currently using the https://github.com/ashleykleynhans/runpod-worker-a1111 along with a network volume. I only use a single model with the sd text2image endpoint and I don't need the UI. Right now, I'm experiencing an 80+ second delay for cold startups on the first request. Do you have any suggestions on how to optimize this (without 1 constant active worker)? Thanks in advance!
11 replies
RRunPod
•Created by heyado on 7/10/2024 in #⚡｜serverless
Can I use a golang handler with serverless?
Tried to find info regarding this: is it possible to use golang for serverless? Any examples in that case?
17 replies
RRunPod
•Created by heyado on 7/3/2024 in #⚡｜serverless
Connection timeout to host - ping errors
I've had these issues from tonight:
2024-07-03 10:06:02.167[nzqh67r97gnbio][error]ERROR | Error while getting job: Connection timeout to host https://api.runpod.ai/v2/f28vlarnz5ud1o/job-take/nzqh67r97gnbio?gpu=NVIDIA+RTX+A4000&job_in_progress=0
2024-07-03 10:06:02.167[nzqh67r97gnbio][error]ERROR | Ping Error: , attempting to restart ping.
Any ideas?
9 replies
