reach-vb HF staff commited on
Commit
38967b8
1 Parent(s): c4fbc17

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -424,6 +424,8 @@ Once a valid PyTorch version is installed, SDPA is activated by default. It can
424
  + model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True, attn_implementation="sdpa")
425
  ```
426
 
 
 
427
  #### Torch compile
428
 
429
  Coming soon...
 
424
  + model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True, attn_implementation="sdpa")
425
  ```
426
 
427
+ For more information about how to use the SDPA refer to the [Transformers SDPA documentation](https://huggingface.co/docs/transformers/en/perf_infer_gpu_one#pytorch-scaled-dot-product-attention).
428
+
429
  #### Torch compile
430
 
431
  Coming soon...