Add latency measurement for text models (#44)

Co-authored-by: Guang Yang <[email protected]>

Author: guangy10

.github/workflows/test_models.yml

@@ -24,6 +24,7 @@ jobs:
           - deit
           - distilbert
           - dit
+          - efficientnet
           - focalnet
           - gemma
           - gemma2
@@ -35,8 +36,10 @@ jobs:
           - pvt
           - qwen2
           - roberta
+          - smollm
           - swin
           - t5
+          - vit
         executorch-version: ['0.4.0', 'nightly']
         python-version: ['3.10', '3.11', '3.12']
         os: [macos-15]
@@ -55,7 +58,7 @@ jobs:
       - name: Install dependencies for ExecuTorch
         run: |
           if [ "${{ matrix.executorch-version }}" == "nightly" ]; then
-            pip install executorch==0.7.0.dev20250330 --extra-index-url "https://download.pytorch.org/whl/nightly/cpu"
+            pip install executorch==0.7.0.dev20250403 --extra-index-url "https://download.pytorch.org/whl/nightly/cpu"
           else
             pip install executorch==${{ matrix.executorch-version }}
           fi

README.md

@@ -152,6 +152,7 @@ We currently support a wide range of popular transformer models, including encod
 - [Cvt](https://huggingface.co/microsoft/cvt-13): Convolutional Vision Transformer
 - [Deit](https://huggingface.co/facebook/deit-base-distilled-patch16-224): Distilled Data-efficient Image Transformer (base-sized)
 - [Dit](https://huggingface.co/microsoft/dit-base-finetuned-rvlcdip): Document Image Transformer (base-sized)
+- [EfficientNet](https://huggingface.co/google/efficientnet-b0): EfficientNet (b0-b7 sized)
 - [Focalnet](https://huggingface.co/microsoft/focalnet-tiny): FocalNet (tiny-sized)
 - [Mobilevit](https://huggingface.co/apple/mobilevit-xx-small): Apple's MobileViT xx-small
 - [Mobilevit2](https://huggingface.co/apple/mobilevitv2-1.0-imagenet1k-256): Apple's MobileViTv2