Do the device_map more automaticlly for multi-GPUs #472
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
The accelerate lib provide some functions to do the device_map automaticlly. This patch use infer_auto_device_map() to relpace the hard codes which splite the mode by hand. It works well with my two GPUs(6GB-RTX3060 + 12GB-RTX3060). Signed-off-by: Alex He <[email protected]>
|
BTW: this is also work for https://github.com/THUDM/ChatGLM-6B. I do not know if I need to do another pull request for ChatGLM-6B repo. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The accelerate lib provides some functions to do the device_map automaticlly. This patch use infer_auto_device_map() to relpace the hard codes which splite the model by hand.
It works well with my two GPUs(6GB-RTX3060 + 12GB-RTX3060).