Files
nvfp4-megamoe-kernel/vllm
biondizzle 21018fca8a fix: shared_experts missing ffn. prefix in checkpoint→model rename
Checkpoint keys are model.layers.N.shared_experts.gate_proj.weight
but model params are layers.N.ffn.shared_experts.gate_up_proj.weight.
The .ffn. was missing from the rename, so stacked gate_up_proj
never matched params_dict.
2026-05-15 00:17:59 +00:00
..