mirror of
https://github.com/deepseek-ai/DeepSeek-VL2.git
synced 2026-11-05 01:07:23 +00:00
[GH-ISSUE #148] How long does it typically take for the vl2-small model to inference a 10*24 image? #122
Labels
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepSeek-VL2#122
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @EvnXie on GitHub (Nov 25, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL2/issues/148
I have deployed the deepseek-vl2-small model locally, using an NVIDIA A100 GPU with 40GB of VRAM. The input image is a 10*24 multi-period K-line chart, and the maximum output token length is 512. The current inference time is around 10 seconds. Is this speed normal? It seems much slower than expected. Could any experts advise on how long this process should generally take? Besides upgrading the GPU, are there any other methods to speed it up?