[CI Failure] Fix test_flashinfer_cutlass_mxfp4_mxfp8_fused_moe (vllm-project#24750)

Signed-off-by: mgoin <[email protected]>
Signed-off-by: bbartels <[email protected]>

Author: mgoin

csrc/attention/mla/sm100_cutlass_mla_kernel.cu

@@ -43,6 +43,7 @@ void sm100_cutlass_mla_decode(
     torch::Tensor const& seq_lens,
     torch::Tensor const& page_table,
     torch::Tensor const& workspace,
+    double sm_scale,
     int64_t num_kv_splits) {
   TORCH_CHECK(false, "CUDA version must be >= 12.4 for cutlass_mla_decode");
 }

tests/kernels/moe/test_mxfp4_moe.py

@@ -771,11 +771,11 @@ def dequant_mxfp4_batches(mat_fp4: torch.Tensor,
     w13_ref = dequant_mxfp4_batches(
         w13_q.view(torch.uint8),
         w13_scale.view(torch.uint8).reshape(-1)).to(torch.float32).reshape(
-            num_experts, 2 * intermediate_size, hidden_size)
+            num_experts, 2 * intermediate_size, hidden_size).to(device)
     w2_ref = dequant_mxfp4_batches(
         w2_q.view(torch.uint8),
         w2_scale.view(torch.uint8).reshape(-1)).to(torch.float32).reshape(
-            num_experts, hidden_size, intermediate_size)
+            num_experts, hidden_size, intermediate_size).to(device)
 
     # Quantize activations for SM100 path and dequantize for reference
     hidden_states_q, hidden_states_sf = mxfp8_quantize(hidden_states, True, 32)