SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Add Aria (#34157)

Browse Source 
* Add Aria
---------

Co-authored-by: Cyril Vallez <cyril.vallez@gmail.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
This commit is contained in:
Aymeric Roucher
2024-12-06 12:17:34 +01:00
committed by GitHub
parent 15ab310c3a
commit 9ad4c93536
32 changed files with 6244 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/perf_infer_gpu_one.md
View File

@@ -37,6 +37,7 @@ FlashAttention-2 is experimental and may change considerably in future versions.
2. partitioning the work between GPU threads to reduce communication and shared memory reads/writes between them
FlashAttention-2 is currently supported for the following architectures:
* [Aria](https://huggingface.co/docs/transformers/model_doc/aria#transformers.AriaForConditionalGeneration)
* [Bark](https://huggingface.co/docs/transformers/model_doc/bark#transformers.BarkModel)
* [Bart](https://huggingface.co/docs/transformers/model_doc/bart#transformers.BartModel)
* [Chameleon](https://huggingface.co/docs/transformers/model_doc/chameleon#transformers.Chameleon)
@@ -216,6 +217,7 @@ PyTorch's [`torch.nn.functional.scaled_dot_product_attention`](https://pytorch.o
For now, Transformers supports SDPA inference and training for the following architectures:
* [Albert](https://huggingface.co/docs/transformers/model_doc/albert#transformers.AlbertModel)
* [Aria](https://huggingface.co/docs/transformers/model_doc/aria#transformers.AriaForConditionalGeneration)
* [Audio Spectrogram Transformer](https://huggingface.co/docs/transformers/model_doc/audio-spectrogram-transformer#transformers.ASTModel)
* [Bart](https://huggingface.co/docs/transformers/model_doc/bart#transformers.BartModel)
* [Bert](https://huggingface.co/docs/transformers/model_doc/bert#transformers.BertModel)