Fix eplb nvfp4 experts hook (#37217)

Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
Signed-off-by: Elvir Crncevic <elvir@anthropic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Elvir Crnčević
2026-03-16 22:03:54 +00:00
committed by GitHub
co-authored by Tyler Michael Smith Claude Opus 4.6
parent c0f011918d
commit fd4d96302a
10 changed files with 57 additions and 25 deletions
@@ -1394,6 +1394,7 @@ class ModelOptNvFp4FusedMoE(FusedMoEMethodBase):
shared_experts=layer.shared_experts,
routing_tables=layer._maybe_init_expert_routing_tables(),
)
self.moe_kernel.fused_experts.process_weights_after_loading(layer)
def get_fused_moe_quant_config(self, layer: torch.nn.Module) -> FusedMoEQuantConfig:
return make_nvfp4_moe_quant_config(