-
Notifications
You must be signed in to change notification settings - Fork 244
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
support OpenGVLab/InternVL-Chat-V1-5 #1490
Conversation
MEAN = (123.675, 116.28, 103.53) | ||
STD = (58.395, 57.12, 57.375) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The two constants, can it be inferred from the Internvl code?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Let's try not to infer any thing from the upstream's repo code. We'd better keep them as independent as possible
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
the mean and std are not in the repo but in the example code.
运行这个代码在输入4通道图像时会报错: 缺少代码: |
@LRHstudy 修好了 |
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
为什么我用tp的话H800每张卡的显存还是吃满了 batch只能跟单张卡还是一样呢 |
多TP的话,是 Tensor Parallel, 每张卡都会算一部分,不管你的batch 是多少。 要控制显存的话,这里提到一些降低显存的方法: LLM 模型 在 tp > 1的时候,每个显卡上的显存是一致。目前vision 模型是挂在0号卡上的,会导致其他卡显存的利用率偏低。这个问题目前正在处理,后面也会让 vision 模型均匀分摊到每个卡上。 |
是这样的 tp=8 和 tp=1的情况下,batch相同的情况下,0卡的显存是一样的,同时1~7也占用了大量的显存,是比0卡小。是哪里没有设置对吗? |
你这个没有问题,符合逻辑。 目前显存分配的逻辑是: tp=8或者1,不影响0号卡剩余的显存大小,所有两种情况显存一样。但是tp=8的时候,因为vision模型目前只在0号卡上,所以1-7上显存会小一些。 |
Motivation
support https://huggingface.co/OpenGVLab/InternVL-Chat-V1-5