Skip to content

Issues: MrYxJ/calculate-flops.pytorch

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.

Sign up for GitHub

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

26 Open 16 Closed
26 Open 16 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

F.scaled_dot_product_attention和q@k这些操作是不是没有被统计？
#48 opened Jan 26, 2025 by huangjch526
1
Can this support calculating FLOPs for LLaVA model?
#47 opened Dec 25, 2024 by donghong1
The FLOPS of scalar dot products in Attention has not been considered？
#46 opened Dec 23, 2024 by XIronMan0220
2
RuntimeError: A view was created in no_grad mode and is being modified inplace with grad mode enabled. Given that this use case is ambiguous and error-prone, it is forbidden. You can clarify your code by moving both the view and the inplace either both inside the no_grad block (if you don't want the inplace to be tracked) or both outside (if you want the inplace to be tracked).
#44 opened Dec 5, 2024 by JokeQ666
1
Compute the FLOPs for each transformer layer of an LLM
#43 opened Nov 4, 2024 by jeremyzhangsq
Ran the example code but got wrong results
#42 opened Oct 15, 2024 by nameongithub
2
AttributeError: 'list' object has no attribute 'shape' in function _einsum_flops_compute()
#40 opened Oct 14, 2024 by Necolizer
1
How to test models deployed on multiple GPUs？
#39 opened Sep 13, 2024 by May2064
packaging.version.InvalidVersion: Invalid version: '0.10.1,<0.11'
#38 opened Sep 11, 2024 by ymmm-4
Flops for GNN
#37 opened Sep 10, 2024 by ritamartinspereira
1
Why are torch.mm and torch.bmm deleted in pytorch_ops.py
#36 opened Aug 13, 2024 by wzk1015
2
Only nn.modules are supported for FLOP analysis?
#35 opened Jul 29, 2024 by avisinghal6
Add support of non-linear operations
#34 opened Jul 16, 2024 by Ther-nullptr
MACs for ConvTranspose2d
#33 opened Jul 5, 2024 by qiuzidian
gated models do not work
#31 opened Jun 26, 2024 by mohbay
1
How to calculate the FLOPs when the model has some freezed variables, or using LoRA?
#30 opened Jun 23, 2024 by Ledzy
On the calculation of FLOPs for SAM/MobileSAM
#29 opened Jun 20, 2024 by BeliverK
你好，比如llama这些LLM模型，我看统计的结果好像没有包括attention矩阵的[email protected]那部分计算量。
#26 opened Jun 7, 2024 by ywh187
5
Can this support StableDiffusion？
#23 opened May 23, 2024 by sunzhe09
1
[Bug] Upsample flops not being assigned after calculation
#22 opened May 14, 2024 by Ridhamz-nd
What is the difference between the 'forward' mode and the 'generate' mode?
#20 opened Apr 7, 2024 by AboveParadise
1
How to calculate model with more than one input?
#17 opened Mar 4, 2024 by yuanzhi-zhu
Why the unit of fwd FLOPs is FLOPS?
#16 opened Feb 19, 2024 by Fibonacci43
1
about 3D object detection
#13 opened Nov 29, 2023 by ouyangziyao
Library diffusers is not supported yet
#12 opened Nov 22, 2023 by XianweiC
3
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.