From 9c07342fdc556efd4b70a6c4183cac699bfcd1cd Mon Sep 17 00:00:00 2001 From: fxmarty-amd Date: Mon, 4 May 2026 22:13:37 +0200 Subject: [PATCH] [NVFP4][fix] Fix `layer.weight` -> `w13` typo in NVFP4 MOE emulation kernel preparation (#41630) Signed-off-by: Felix Marty --- vllm/model_executor/layers/fused_moe/oracle/nvfp4.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/model_executor/layers/fused_moe/oracle/nvfp4.py b/vllm/model_executor/layers/fused_moe/oracle/nvfp4.py index 01ac5cfa9da..f4796243e01 100644 --- a/vllm/model_executor/layers/fused_moe/oracle/nvfp4.py +++ b/vllm/model_executor/layers/fused_moe/oracle/nvfp4.py @@ -381,7 +381,7 @@ def convert_to_nvfp4_moe_kernel_format( elif nvfp4_backend == NvFp4MoeBackend.EMULATION: # Move the E2M1 lookup table to the device now, because # `.to(device)` is not allowed during CUDA graph capture. - kE2M1ToFloat_handle.val = kE2M1ToFloat_handle.val.to(layer.weight.device) + kE2M1ToFloat_handle.val = kE2M1ToFloat_handle.val.to(w13.device) if a13_scale is None or a2_scale is None: raise ValueError(