iree-org/iree

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

Open

#9.190 aberto em 23 de mai. de 2022

Ver no GitHub
 (3 comments) (0 reactions) (2 assignees)C++ (918 forks)github user discovery
bug 🐞help wantedintegrations/tosa

Métricas do repositório

Stars
 (3.787 stars)
Métricas de merge de PR
 (Métricas PR pendentes)

Description

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>

Guia do colaborador