under test, not sure no errors

upstream_ref/fla/modules/__init__.py

@@ -0,0 +1,52 @@
+# Copyright (c) 2023-2026, Songlin Yang, Yu Zhang, Zhiyuan Li
+#
+# This source code is licensed under the MIT license found in the
+# LICENSE file in the root directory of this source tree.
+# For a list of all contributors, visit:
+#   https://github.com/fla-org/flash-linear-attention/graphs/contributors
+
+from fla.modules.convolution import ImplicitLongConvolution, LongConvolution, ShortConvolution
+from fla.modules.fused_bitlinear import BitLinear, FusedBitLinear
+from fla.modules.fused_cross_entropy import FusedCrossEntropyLoss
+from fla.modules.fused_kl_div import FusedKLDivLoss
+from fla.modules.fused_linear_cross_entropy import FusedLinearCrossEntropyLoss
+from fla.modules.fused_norm_gate import (
+    FusedLayerNormGated,
+    FusedLayerNormSwishGate,
+    FusedLayerNormSwishGateLinear,
+    FusedRMSNormGated,
+    FusedRMSNormSwishGate,
+    FusedRMSNormSwishGateLinear,
+)
+from fla.modules.l2norm import L2Norm
+from fla.modules.layernorm import GroupNorm, GroupNormLinear, LayerNorm, LayerNormLinear, RMSNorm, RMSNormLinear
+from fla.modules.mlp import GatedMLP
+from fla.modules.rotary import RotaryEmbedding
+from fla.modules.token_shift import TokenShift
+
+__all__ = [
+    'BitLinear',
+    'FusedBitLinear',
+    'FusedCrossEntropyLoss',
+    'FusedKLDivLoss',
+    'FusedLayerNormGated',
+    'FusedLayerNormSwishGate',
+    'FusedLayerNormSwishGateLinear',
+    'FusedLinearCrossEntropyLoss',
+    'FusedRMSNormGated',
+    'FusedRMSNormSwishGate',
+    'FusedRMSNormSwishGateLinear',
+    'GatedMLP',
+    'GroupNorm',
+    'GroupNormLinear',
+    'ImplicitLongConvolution',
+    'L2Norm',
+    'LayerNorm',
+    'LayerNormLinear',
+    'LongConvolution',
+    'RMSNorm',
+    'RMSNormLinear',
+    'RotaryEmbedding',
+    'ShortConvolution',
+    'TokenShift',
+]

upstream_ref/fla/modules/convolution.py

@@ -0,0 +1,42 @@
+# Copyright (c) 2023-2026, Songlin Yang, Yu Zhang, Zhiyuan Li
+#
+# This source code is licensed under the MIT license found in the
+# LICENSE file in the root directory of this source tree.
+# For a list of all contributors, visit:
+#   https://github.com/fla-org/flash-linear-attention/graphs/contributors
+
+from fla.modules.conv import (
+    ImplicitLongConvolution,
+    LongConvolution,
+    PositionalEmbedding,
+    ShortConvolution,
+    causal_conv1d,
+    fft_conv,
+)
+from fla.modules.conv.cp import CausalConv1dFunctionCP, causal_conv1d_cp
+from fla.modules.conv.cuda import FastCausalConv1dFn, fast_causal_conv1d_fn
+from fla.modules.conv.triton import (
+    CausalConv1dFunction,
+    causal_conv1d_bwd,
+    causal_conv1d_fwd,
+    causal_conv1d_update,
+    causal_conv1d_update_states,
+)
+
+__all__ = [
+    'CausalConv1dFunction',
+    'CausalConv1dFunctionCP',
+    'FastCausalConv1dFn',
+    'ImplicitLongConvolution',
+    'LongConvolution',
+    'PositionalEmbedding',
+    'ShortConvolution',
+    'causal_conv1d',
+    'causal_conv1d_bwd',
+    'causal_conv1d_cp',
+    'causal_conv1d_fwd',
+    'causal_conv1d_update',
+    'causal_conv1d_update_states',
+    'fast_causal_conv1d_fn',
+    'fft_conv',
+]