openreasoner / openr

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
https://openreasoner.github.io/
MIT License
1.07k stars 79 forks source link

How much video memory is required for a single card to run two models? #38

Open reedest7 opened 3 weeks ago

reedest7 commented 3 weeks ago

System Info

single card 3090,video memory 24GB

Who can help?

No response

Information

Tasks

Reproduction

POLICY_MODEL=Qwen2.5-Math-1.5B-Instruct;VALUE_MODEL_NAME=math-shepherd-mistral-7b-prm。When running sh reason/llm/service/generate_service_math_sthepherd.sh, only vllmw_worker can be started and the reward model cannot be started. Error OOM reported. 1

Expected behavior

May I ask how much video memory is required for a single card to run two models

caihuaiguang commented 3 weeks ago

2 48G GPUs (this is my device setting), to run the service (sh reason/llm_service/create_service_math_shepherd.sh), with RM and LM models on separate GPU.

Dada-Cloudzxy commented 1 week ago

The 1.5B model actually runs the entire A100_80G( inference service, 4 lm_workers in 4 GPUs ).