iree-org/iree

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

Open

#9,190 建立於 2022年5月23日

在 GitHub 查看
 (3 留言) (0 反應) (2 負責人)C++ (918 fork)github user discovery
bug 🐞help wantedintegrations/tosa

倉庫指標

Star
 (3,787 star)
PR 合併指標
 (PR 指標待抓取)

描述

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>

貢獻者指南