Add gradient checkpointing for DINOv3 and DGTRS-CLIP (bs 8→24)

- DINOv3: checkpoint each of 24 transformer blocks (recompute on backward)
- DGTRS-CLIP: checkpoint each of 12 transformer blocks
- Enables batch_size=24 on RTX 4090 (was 8 without checkpointing)
- Peak VRAM: 20.3 GB at bs=24 (was OOM at bs=16 before)
- ~20-30% slower per step, but 3x more in-batch negatives (23 vs 7)
- Enabled by default (gradient_checkpointing=True in config)
- Update README with VRAM benchmarks and checkpointing docs

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/models/asymmetric_encoder.py

@@ -169,12 +169,22 @@ class DINOv3ViT(nn.Module):
         ])
         self.norm = nn.LayerNorm(dim)
         self.embed_dim = dim
+        self.gradient_checkpointing = False
+
+    def set_gradient_checkpointing(self, enable: bool = True) -> None:
+        """Enable/disable gradient checkpointing to trade compute for VRAM."""
+        self.gradient_checkpointing = enable
 
     def forward(self, x: torch.Tensor) -> torch.Tensor:
         """Forward pass. Returns CLS token embedding [B, dim]."""
         x = self.embeddings(x)
         for block in self.layer:
-            x = block(x)
+            if self.gradient_checkpointing and self.training:
+                x = torch.utils.checkpoint.checkpoint(
+                    block, x, use_reentrant=False,
+                )
+            else:
+                x = block(x)
         x = self.norm(x)
         return x[:, 0]  # CLS token
 

src/models/dgtrs/model.py

@@ -77,8 +77,15 @@ class Transformer(nn.Module):
         self.resblocks = nn.Sequential(
             *[ResidualAttentionBlock(width, heads, attn_mask) for _ in range(layers)]
         )
+        self.gradient_checkpointing = False
 
     def forward(self, x: torch.Tensor):
+        if self.gradient_checkpointing and self.training:
+            for block in self.resblocks:
+                x = torch.utils.checkpoint.checkpoint(
+                    block, x, use_reentrant=False,
+                )
+            return x
         return self.resblocks(x)