请问将视觉模型参数均匀分到多张GPU上的例子在哪里? #3205
Replies: 1 comment
-
当引擎是 turbomind engine 时,vision 模型的forward是复用的上游库,会把视觉模型通过 accelerate 切到不同的 rank上。 lmdeploy/lmdeploy/vl/model/internvl.py Line 129 in ef0cfe7 当引擎是 pytorch engine,vision 模型的forward在引擎中实现,权重已 tensor parallel 的方式切分到不同 rank 上。 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
请问有视觉模型参数均匀分到多张GPU上的例程么
Beta Was this translation helpful? Give feedback.
All reactions