[bugfix] Fix dead NVFP4 QAT plumbing: bench imports, int8 error string, smooth_q crash (#1723)

fastvideo-kernel/python/fastvideo_kernel/triton_kernels/attn_qat_train.py

@@ -1054,6 +1054,15 @@ class _attention(torch.autograd.Function):
         use_global_sf_P=True,
         use_global_sf_QKV=True,
     ):
+        if smooth_q:
+            # Not implemented, not merely disabled: only the backward kernels
+            # carry a SMOOTH_Q path (_attn_fwd has none), so restoring the
+            # triton_group_mean wiring would yield silently wrong gradients
+            # rather than a feature. The flag is kept for signature
+            # compatibility only.
+            raise NotImplementedError("smooth_q=True is not supported: the forward kernel has no "
+                                      "SMOOTH_Q path, so enabling it would produce incorrect gradients")
+
         # shape constraints
         HEAD_DIM_Q, HEAD_DIM_K = q.shape[-1], k.shape[-1]
         # when v is in float8_e5m2 it is transposed.
@@ -1364,10 +1373,8 @@ class _attention(torch.autograd.Function):
                                        BLOCK_M=PRE_BLOCK,
                                        HEAD_DIM=ctx.HEAD_DIM)
 
+        # smooth_q is rejected in forward(); ctx.smooth_q is always False here.
         q_m = None
-        if ctx.smooth_q:
-            # _, q_m = triton_group_mean(q)
-            q_m = q_m.repeat_interleave(q.shape[2] // q_m.shape[2], dim=2)  # B,H,L,D
 
         sm100_optimized_backward = (getattr(ctx, "sm100_optimized", False) and ctx.use_qat_qkv_backward
                                     and not ctx.smooth_k and not ctx.smooth_q and N_CTX_KV % 16 == 0)