eosphoros-ai/DB-GPT

[BUG]: When using DB-GPT, with the continuous questioning, CUDA memory has been increasing until memory exploded

Open

#147 opened on Jun 2, 2023

View on GitHubContributor guide
 (2 comments) (0 reactions) (0 assignees)Python (2,879 forks)batch import
enhancementgood first issue

Repository metrics

Stars
 (19,732 stars)
PR merge metrics
 (Avg merge 5d 22h) (5 merged PRs in 30d)

Description

Follow the tutorial to deploy DB-GPT on the ubuntu machine, 24g single-card GPU. As I continued to ask questions, CUDA memory kept increasing until memory exploded. How to free video memory?

Contributor guide

Research direction
Trace CUDA memory allocations during model inference to identify which tensors or intermediate results are not freed. Check for retained references in the conversation loop or caching mechanism.
Tech stack
python
Domain
backendai infra agents
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
Python
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50