Models · Classification

EfficientViT (MIT)

EfficientViT (Cai et al. 2023, MIT Han lab): a classifier with multi-scale linear attention.

Commercial use: yes.

variantinputbackendtime (ms)peak memory (MiB, allocated / reserved)
efficientvit_b2.r288_in1ksynthetic (224x224)original (fp32)
original
portable
kernels
portable + torch.compile
TensorRT fp16		10.7
14.7
11.9
1.10
6.91
0.790		144 / 160
173 / 194
85 / 124
120 / 212
120 / 164
74 (engine)
Details
  • Original code: https://github.com/huggingface/pytorch-image-models at 0df212b369a5
  • Code licence: Apache-2.0 (permissive); files:
  • Weights licence: Apache-2.0
  • Licence evidence: https://huggingface.co/timm/efficientvit_b2.r288_in1k/blob/891530d0c5a400dd2d4549c81d433661b192abe1/README.md
  • Training data: ImageNet-1k (ILSVRC 2012 classification)
  • Kernel libraries: cudnn_hacc, fvm_conv, fvm_extra, fvm_mb, fvm_r3
  • Variants: efficientvit_b2.r288_in1k (default of efficientvit_b2)
  • Outputs: logits; label_set: imagenet-1k
  • Input size: fixed 288x288: the input is resized (short side 288) and centre-cropped to it
  • Tested up to (portable, fp16, RTX 5060 Ti 16 GB): efficientvit_b2.r288_in1k 288x288 (0.1 GiB peak allocated, 0.1 reserved)
  • efficientvit_b2.r288_in1k 224x224, first call: portable + torch.compile 11 s (cold Inductor cache), TensorRT fp16 35 s (ONNX + engine).
  • efficientvit_b2.r288_in1k original 224x224: torch.autocast(fp16) around the forward
  • efficientvit_b2.r288_in1k load / first call: original 1.84 s / 1.888 s, portable 0.4 s / 0.039 s, kernels 1.92 s / 0.051 s
  • Protocol, median of 9 after 3 warm-up, uint8 CUDA input (synthetic for bench_inputs sizes), card defaults; gc before each load; peak = max over the first call and the timed calls

Measured

fastforks: the model's own resize / crop on the GPU; original: the library's pretrained loader and its PIL eval transform. Original = the original code named under Details, same checkpoint and protocol.

variantdatasetoriginal fp32original fp16portablekernelsnote
efficientvit_b2.r288_in1kImageNet-1k val, 5000 random images, top-1 / top-5 %84.28 / 96.6484.26 / 96.6484.22 / 96.6484.28 / 96.60

Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 939adfe8, 2026-11-06.

Parity

CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.05 and p99 <= 0.2 (absolute error of the output logits).

variantkernels error vs original, mean / p99GPU, torchkernels used
efficientvit_b2.r288_in1k0.01737 / 0.06142RTX 5060 Ti, torch 2.14.1+cu130cudnn_hacc@cudnn92400, fvm_conv@f1d064e539e1:sm_120, fvm_extra@3208ce525a91:sm_120, fvm_mb@720dd3f29bf7:sm_120, fvm_r3@f54eb890e23c:sm_120