patch

Two related bugs in vivit.py:

1. Transformer.__init__ accepted use_flash_attn but never forwarded it to the
   Attention modules it creates. Since Attention defaults to use_flash_attn=True,
   setting use_flash_attn=False on ViViT had no effect on the factorized_encoder
   variant's spatial and temporal transformers.

2. Attention.forward reshaped the mask from 2D to 4D before the flash/non-flash
   branch (line 82), then attempted to reshape it again inside the non-flash
   branch (line 92). When the non-flash code path is actually reached with a
   mask, einops raises an error because the mask is already 4D.

   These bugs masked each other: bug #1 prevented bug #2 from triggering because
   the non-flash path was never taken even when requested.

Fix: pass use_flash_attn through to Attention in Transformer.__init__, and
remove the redundant second mask rearrange in the non-flash branch.

README.md

@@ -2237,4 +2237,16 @@ Coming from computer vision and new to transformers? Here are some resources tha
 }
 ```
 
+```bibtex
+@misc{chen2026postlayernormbackstableexpressive,
+    title   = {Post-LayerNorm Is Back: Stable, ExpressivE, and Deep}, 
+    author  = {Chen Chen and Lai Wei},
+    year    = {2026},
+    eprint  = {2601.19895},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.LG},
+    url     = {https://arxiv.org/abs/2601.19895}, 
+}
+```
+
 *I visualise a time when we will be to robots what dogs are to humans, and I’m rooting for the machines.* — Claude Shannon

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "vit-pytorch"
-version = "1.17.6"
+version = "1.17.8"
 description = "Vision Transformer (ViT) - Pytorch"
 readme = { file = "README.md", content-type = "text/markdown" }
 license = { file = "LICENSE" }

vit_pytorch/vit_with_keel_post_ln.py

@@ -0,0 +1,217 @@
+from __future__ import annotations
+
+import torch
+from torch import nn
+from torch.nn import Module, ModuleList
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# functions
+
+def exists(v):
+    return v is not None
+
+def default(v, d):
+    return v if exists(v) else d
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# classes
+
+class FeedForward(Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim, bias = False),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.norm = nn.LayerNorm(dim, bias = False)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        x = self.norm(x)
+
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(Module):
+    def __init__(
+        self,
+        dim,
+        depth,
+        heads,
+        dim_head,
+        mlp_dim,
+        dropout = 0.,
+        keel_residual_scale = None
+    ):
+        super().__init__()
+        assert depth > 1
+
+        self.layers = ModuleList([])
+
+        for _ in range(depth):
+            self.layers.extend([
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
+            ])
+
+        num_layers = depth * 2
+        self.keel_residual_scale = default(keel_residual_scale, num_layers)
+
+        self.post_norms = ModuleList([nn.LayerNorm(dim, bias = False) for _ in range(num_layers - 1)])
+
+    def forward(self, x):
+        residual_scale = self.keel_residual_scale
+
+        for layer_ind, layer in enumerate(self.layers):
+            first_layer = layer_ind == 0
+        
+            residual = x
+
+            out = layer(x)
+
+            if first_layer:
+                x = out + residual
+                continue
+
+            post_norm = self.post_norms[layer_ind - 1]
+
+            x = post_norm(out + residual * residual_scale)
+
+        return x
+
+class ViT(Module):
+    def __init__(
+        self,
+        *,
+        image_size,
+        patch_size,
+        num_classes,
+        dim,
+        depth,
+        heads,
+        mlp_dim,
+        pool = 'cls',
+        channels = 3,
+        dim_head = 64,
+        dropout = 0.,
+        emb_dropout = 0.,
+        keel_residual_scale = None
+    ):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+        num_cls_tokens = 1 if pool == 'cls' else 0
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.cls_token = nn.Parameter(torch.randn(num_cls_tokens, dim))
+        self.pos_embedding = nn.Parameter(torch.randn(num_patches + num_cls_tokens, dim))
+
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(
+            dim,
+            depth,
+            heads,
+            dim_head,
+            mlp_dim,
+            dropout,
+            keel_residual_scale = keel_residual_scale
+        )
+
+        self.pool = pool
+        self.to_latent = nn.Identity()
+
+        self.mlp_head = nn.Linear(dim, num_classes) if num_classes > 0 else None
+
+    def forward(self, img):
+        batch = img.shape[0]
+        x = self.to_patch_embedding(img)
+
+        cls_tokens = repeat(self.cls_token, '... d -> b ... d', b = batch)
+        x = torch.cat((cls_tokens, x), dim = 1)
+
+        seq = x.shape[1]
+
+        x = x + self.pos_embedding[:seq]
+        x = self.dropout(x)
+
+        x = self.transformer(x)
+
+        if not exists(self.mlp_head):
+            return x
+
+        x = x.mean(dim = 1) if self.pool == 'mean' else x[:, 0]
+
+        x = self.to_latent(x)
+        return self.mlp_head(x)
+
+if __name__ == '__main__':
+    v = ViT(
+        image_size = 256,
+        patch_size = 32,
+        num_classes = 1000,
+        dim = 1024,
+        depth = 6,
+        heads = 16,
+        mlp_dim = 2048,
+        dropout = 0.1,
+        emb_dropout = 0.1
+    )
+
+    img = torch.randn(1, 3, 256, 256)
+
+    preds = v(img)
+
+    assert preds.shape == (1, 1000)

vit_pytorch/vivit.py

@@ -89,7 +89,6 @@ class Attention(Module):
             dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
 
             if exists(mask):
-                mask = rearrange(mask, 'b j -> b 1 1 j')
                 dots = dots.masked_fill(~mask, -torch.finfo(dots.dtype).max)
 
             attn = self.attend(dots)
@@ -109,7 +108,7 @@ class Transformer(Module):
         self.layers = ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout, use_flash_attn = use_flash_attn),
                 FeedForward(dim, mlp_dim, dropout = dropout)
             ]))