Skip to content

Issues: lucidrains/performer-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

43 Open 43 Closed
43 Open 43 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

Find FastAttention is slower, and also with more GPU memory usage
#97 opened Nov 19, 2024 by phyllispeng123
Separate Transformer Encoder & Decoder modules with linear attention?
#96 opened Aug 28, 2024 by harshakmohan
Modify the transformer tutorial based on performer
#95 opened May 20, 2023 by HelloWorldLTY
Cross-attention with arbitrary causal mask
#94 opened Apr 25, 2023 by BarKetPlace
Pretrained example
#93 opened Dec 19, 2022 by jubueche
Performer Pytorch Slower than Expected and Please Help with Understanding Parameter Count
#92 opened Dec 12, 2022 by michaelweihaosong
1
Using replicating nn.MultiHeadAttention with multiple performer SelfAttention modules
#91 opened Dec 6, 2022 by JGittles
I want to use Peroformer on MAE
#90 opened Nov 4, 2022 by Zhaoyi-Yan
Question about masking
#89 opened Jul 21, 2022 by Microbiods
2
Question: Is Performer order equivariant? (can it transform an unordered set of tensors)
#88 opened Jul 15, 2022 by nmakes
Using Performer with GNNs
#87 opened May 3, 2022 by jah377
Huge model state dict size?
#86 opened Apr 14, 2022 by Liyue1d
Performer Plain
#84 opened Mar 28, 2022 by Rachel66666
How to test the performer architecture for training new models?
#83 opened Feb 3, 2022 by ayan-iiitd
1
Output inconsistent for autoregressive performer
#82 opened Jan 24, 2022 by GanjinZero
2
Rotary Position Embedding
#81 opened Jan 5, 2022 by ahmdtaha
torch_tensorrt compilation fails
#80 opened Dec 20, 2021 by FredHaa
way to make two elements invisible?
#79 opened Nov 22, 2021 by 1140310118
hyperbolic cosine based estimator
#73 opened Jul 9, 2021 by gaganbahga
Names to_k, to_q, to_v, to_out cause issues
#71 opened Jun 4, 2021 by JamesDeAntonis
Recover attention scores
#70 opened Jun 1, 2021 by carlomarxdk
3
FastAttention doesn't give results in agreement with standard attention?
#69 opened May 28, 2021 by simonaxelrod
7
Performer Benchmark
#67 opened May 5, 2021 by CavallucciMartina
Causal performer slower than causal regular attention
#66 opened Apr 23, 2021 by JamesDeAntonis
3
Decoder Mask
#62 opened Mar 5, 2021 by Muennighoff
ProTip! Mix and match filters to narrow down what you’re looking for.