open-compass / open-compass/VLMEvalKit
4090上使用vllm评估会oom
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 4.4k
- Forks
- 768
- Avg merge
- 1d 10h
- Merged PRs (30d)
- 17
Description
CUDA_VISIBLE_DEVICES=1 python run.py
--data MMBench_TEST_EN_V11 MMBench_TEST_CN_V11 CCBench
--model MIS-Qwen2.5-VL-7B
--use-vllm
--api-nproc 1
--verbose
好像是max-token的问题，这个在哪设置？
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by running the reported command in run.py with the MMBench and CCBench arguments, then trace how --use-vllm handles token limits and memory settings. Identify where the maximum-token value is configured and verify a documented setting or change prevents the 4090 evaluation from running out of memory.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100