[model] fix: restore explicit gradient_accumulation_fusion=True overrides

The dynamic checker (can_enable_gradient_accumulation_fusion) is
unreliable in the training environment — it returns False even when the
fused_weight_gradient_mlp_cuda extension is available at runtime.
Restore explicit True overrides in DSV2, DSV3, Kimi bridges and NT3
Nano recipe to guarantee the fusion is always enabled for these models.

Signed-off-by: Yu Yao <yaoyu.094@gmail.com>
Signed-off-by: yaoyu-33 <yaoyu.094@gmail.com>

Author: yaoyu-33

src/megatron/bridge/models/deepseek/deepseek_v2_bridge.py

@@ -62,6 +62,7 @@ def provider_bridge(self, hf_pretrained: PreTrainedCausalLM) -> MLAModelProvider
         provider.moe_permute_fusion = True
 
         provider.apply_rope_fusion = False
+        provider.gradient_accumulation_fusion = True
         provider.bias_activation_fusion = True
         provider.bias_dropout_fusion = True
         provider.cross_entropy_fusion_impl = "te"

src/megatron/bridge/models/deepseek/deepseek_v3_bridge.py

@@ -69,6 +69,7 @@ def provider_bridge(self, hf_pretrained: PreTrainedCausalLM) -> MLAModelProvider
         provider.moe_aux_loss_coeff = 0.0001
 
         provider.apply_rope_fusion = False
+        provider.gradient_accumulation_fusion = True
         provider.bias_activation_fusion = True
         provider.bias_dropout_fusion = True
         provider.cross_entropy_fusion_impl = "te"

src/megatron/bridge/models/kimi/kimi_bridge.py

@@ -64,6 +64,7 @@ def provider_bridge(self, hf_pretrained: PreTrainedCausalLM) -> MLAModelProvider
         provider.moe_permute_fusion = True
 
         provider.apply_rope_fusion = False
+        provider.gradient_accumulation_fusion = True
         provider.bias_activation_fusion = True
         provider.bias_dropout_fusion = True
         provider.cross_entropy_fusion_impl = "te"

src/megatron/bridge/recipes/nemotronh/nemotron_3_nano.py

@@ -187,6 +187,7 @@ def nemotron_3_nano_pretrain_config() -> ConfigContainer:
 
     cfg.model.init_method_std = 0.0173
     cfg.model.apply_rope_fusion = False
+    cfg.model.gradient_accumulation_fusion = True
     cfg.model.use_fused_weighted_squared_relu = True
 
     return cfg
@@ -299,6 +300,7 @@ def nemotron_3_nano_sft_config() -> ConfigContainer:
     cfg.model.moe_grouped_gemm = True
     cfg.model.cross_entropy_loss_fusion = True
     cfg.model.cross_entropy_fusion_impl = "native"
+    cfg.model.gradient_accumulation_fusion = True
 
     # Memory saving (recompute & offloading)
     cfg.model.recompute_granularity = None
@@ -488,6 +490,7 @@ def nemotron_3_nano_peft_config(
     cfg.model.moe_grouped_gemm = True
     cfg.model.cross_entropy_loss_fusion = True
     cfg.model.cross_entropy_fusion_impl = "native"
+    cfg.model.gradient_accumulation_fusion = True
 
     # Memory saving
     cfg.model.recompute_granularity = None