InternLM / InternLM/lmdeploy

[Bug] The script "profile_generation.py" went haywire and crashed

Open
#2,760 2 comments 0 reactions 1 assignee Claimed by @jinminxi104 View on GitHub
Dominant language
Python
Stars
8.1k
Forks
748
Avg merge
6d 2h
Merged PRs (30d)
54

Description

### Checklist

- [X] 1. I have searched related issues but cannot get the expected help.
- [X] 2. The bug has not been fixed in the latest version.
- [X] 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.

### Describe the bug

if set c(concurrency) large, crashed, maybe kv_cache is not enough, but there is no clear indication.
Run script as below:
1731651728196
Traceback:
1731651803543

### Reproduction

python benchmark/profile_generation.py /data/models/Qwen2.5-14B-Instruct --backend pytorch -pt 2048 -ct 512 -c 128 --tp 1

### Environment

```Shell
maca C500 GPU.
```

### Error traceback

_No response_

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.