© 2026 Hedgehog Software, LLC

Twitter GitHub Discord

More

Communities Docs About Terms Privacy

Veryyyyyy slow serverless VLLM - Runpod

Runpod•10mo ago•

50 replies

Veryyyyyy slow serverless VLLM

Considering moving away from RunPod, this is just insane how slow this is on serverless

Runpod serverless 4090 GPU, cold start of vllm:
Model loading took 7.5552 GiB and 52.588290 seconds

My local 3090 cold start of vllm
Model loading took 7.5552 GiB and 1.300690 seconds

¿any idea?

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

21,202Members

Resources

Recent Announcements

Similar Threads

Was this page helpful?

Similar Threads

Serverless VLLM batching

RRunpod / ⚡｜serverless

Serverless vllm - lora

RRunpod / ⚡｜serverless

vLLM Serverless error

RRunpod / ⚡｜serverless

Serverless VLLM concurrency issue

RRunpod / ⚡｜serverless