Disable chunked_forward() on AVX512 CPUs #179
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
borzunov
commented
Jan 4, 2023
| if self.word_embeddings.weight.numel() * 4 < 0.9 * psutil.virtual_memory().total: | ||
| logger.warning( | ||
| "Running the client with dtype bfloat16 on CPU may be slow, since your CPU doesn't support AVX512. " | ||
| "Consider loading the model with torch_dtype='float32'" |
There was a problem hiding this comment.
In future, we can also suggest to use fast_but_approximate=True here, which will run faiss under the hood for greedy and top_k generation
borzunov
force-pushed
the
no-chunked-forward-on-avx512
branch
from
203e2ca
to
ce76beb
Compare
borzunov
force-pushed
the
no-chunked-forward-on-avx512
branch
from
ce76beb
to
7880687
Compare
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Outdated suggestions cannot be applied.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.
See benchmarks in #176.