VLM inference performance
Open
- Dominant language
- Python
- Stars
- 8.1k
- Forks
- 748
- Avg merge
- 6d 2h
- Merged PRs (30d)
- 54
Description
I use Qwen2-vl-2b to do classification task, latency 300ms and QPS 5 with A10
is the performance normal?
quantize awq
"max_pixels": 256*28*28
prompt text 100 token
inference tokens 20
Contributor guide
Assessment
This issue has not been assessed yet.