fix: add missing use_deterministic_attn parameter to MoonViT3dEncoder

MoonViT3dEncoder.__init__ references self.use_deterministic_attn on line 575
when constructing the MoonViTEncoderLayer blocks, but the attribute is never
set on self. Loading the model via AutoModelForCausalLM with
trust_remote_code=True raises:

AttributeError: 'MoonViT3dEncoder' object has no attribute
'use_deterministic_attn'

The sibling class MoonViTEncoderLayer already accepts use_deterministic_attn
as a keyword parameter with default False, so the attribute on the parent
3d-encoder was clearly intended to plumb through the same flag. Restore the
missing parameter with the same default.

Production serving paths (vLLM's Kimi-K25 model executor) bypass the HF
custom modeling init and construct the vision tower differently, so this
bug is invisible at serving time but blocks transformers-based workflows
like ModelOpt NVFP4 quantization and HF-native fine-tuning.

Identical fix already merged in Kimi-K2.5 PR #91 (by @katuni4ka , approved
by @fxmarty-amd ). This mirrors it to K2.6 byte-for-byte.

Minimal repro:

from transformers import AutoModelForCausalLM
AutoModelForCausalLM.from_pretrained(
"moonshotai/Kimi-K2.6", trust_remote_code=True, torch_dtype="auto",
)

modeling_kimi_k25.py

@@ -562,7 +562,8 @@ class MoonViT3dEncoder(nn.Module):
                  hidden_dim: int,
                  num_layers: int,
                  block_cfg: dict,
-                 video_attn_type: str = 'spatial_temporal') -> None:
+                 video_attn_type: str = 'spatial_temporal',
+                 use_deterministic_attn: bool = False) -> None:
         super().__init__()
 
         assert video_attn_type == 'spatial_temporal', f'video_attn_type must be "spatial_temporal", got {video_attn_type}'
@@ -572,7 +573,7 @@ class MoonViT3dEncoder(nn.Module):
         self.blocks = nn.ModuleList([
             MoonViTEncoderLayer(
                 **block_cfg,
-                use_deterministic_attn=self.use_deterministic_attn)
+                use_deterministic_attn=use_deterministic_attn)
             for _ in range(num_layers)
         ])
         self.final_layernorm = nn.LayerNorm(hidden_dim)