iree-org/iree

[TFL] `tfl.lstm` should have a stateful decomposition to other TFLite operations

Open

#9190 aperta il 23 mag 2022

Vedi su GitHub
 (3 commenti) (0 reazioni) (2 assegnatari)C++ (918 fork)github user discovery
bug 🐞help wantedintegrations/tosa

Metriche repository

Star
 (3787 star)
Metriche merge PR
 (Merge medio 5g 23h) (54 PR mergiate in 30 g)

Descrizione

Some significant models are blocked by tfl.lstm which can be decomposed into already support tflite operations. Adding the decomposition should unblock these models.

/tmp/test.tflite:0:0: note: see current operation: %95 = "tfl.lstm"(%arg0, %44, %42, %41, %40, %44, %39, %38, %37, %44, %44, %44, %44, %92, %91, %90, %36, %44, %89, %88, %44, %87, %86, %85) ({
}) {asymmetric_quantize_inputs = false, cell_clip = 1.000000e+01 : f32, fused_activation_function = "TANH", kernel_type = "FULL", proj_clip = 0.000000e+00 : f32} : (tensor<1x1280xf32>, none, tensor<2048x1280xi8>, tensor<2048x1280xi8>, tensor<2048x1280xi8>, none, tensor<2048x640xi8>, tensor<2048x640xi8>, tensor<2048x640xi8>, none, none, none, none, tensor<2048xf32>, tensor<2048xf32>, tensor<2048xf32>, tensor<640x2048xi8>, none, tensor<1x640xf32>, tensor<1x2048xf32>, none, tensor<2048xf32>, tensor<2048xf32>, tensor<2048xf32>) -> tensor<*xf32>

Guida contributor