[CLI] Use auto device map for model load #1596
Merged
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
lewtun
commented
Apr 28, 2024
| @@ -220,7 +220,7 @@ def load_model_and_tokenizer(args): | |||
| trust_remote_code=args.trust_remote_code, | |||
| attn_implementation=args.attn_implementation, | |||
| torch_dtype=torch_dtype, | |||
| device_map=get_kbit_device_map() if quantization_config is not None else None, | |||
There was a problem hiding this comment.
I don't think the k-bit device map is actually needed for inference (one can shard and quantize AFAIK)
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
younesbelkada
approved these changes
Apr 30, 2024
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Outdated suggestions cannot be applied.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.
As a user of the chat CLI, I expect the model to be loaded on GPU by default instead of having to manually specify
--device "cuda"I believe this can be achieved by simply setting
device_map="auto"which will also work on CPU if the user should require it.