Update code and README #122
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
facebook-github-bot
added
the
CLA Signed
|
Hi @cpuhrsch , could you please take a look? Thanks! |
cpuhrsch
reviewed
May 31, 2024
experiments/eval_combo.py
Outdated
| total_memory = psutil.virtual_memory().total | ||
| max_memory_allocated_bytes = resource.getrusage(resource.RUSAGE_SELF).ru_maxrss | ||
| max_memory_allocated_percentage = int(100 * (max_memory_allocated_bytes / (total_memory >> 10))) | ||
| max_memory_allocated_bytes = max_memory_allocated_bytes >> 10 | ||
|
|
||
| if print_header: | ||
| print(",".join(["sam_model_type", "batch_size", "memory(MiB)", "memory(%)", "img_s(avg)", "batch_ms(avg)/batch_size", "mIoU", "use_compile", |
There was a problem hiding this comment.
Is there something you could add to indicate the device? Seems like this needs a new column to track the device used.
There was a problem hiding this comment.
Yes, of course. I just add device at the front.
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Outdated suggestions cannot be applied.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.
This PR is to update README of PyTorch nightly version, and update some codes related to CPU support.
We have optimized attn_mask in SDPA with block-wise algorithm in pytorch/pytorch#126961. It can reduce memory peak usage, and have some performance improvements as below.
Performance
Single socket in Intel (R) Xeon (R) CPU Max 9480
Dtype: bfloat16, models: vit_b and vit_h, test in
SDPAandTritoncommit https://github.com/pytorch-labs/segment-anything-fast/blob/main/experiments/run_experiments.py#L199-L200, select the time of 20th iteration.