moe(wip): zero dequant output — decode STILL broken (not fixed)

Tried Tensor::zeros (instead of empty) for the dequant output on the theory
that decode read uninitialized memory. It did NOT fix it: decode top-1 still
diverges from the forward reference AND is still non-deterministic run-to-run
(top-1 varied across runs), generation still garbage. So the bug is NOT a
dequant-output init issue. Root cause remains OPEN. Forward (host attention)
remains correct ("Paris"); only the KV-cache decode path is wrong.
Do not trust decode output.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

crates/xserv-kernels/src/quant.rs

@@ -25,7 +25,8 @@ pub fn dequant_mxfp4(
     blocks: &GpuBuffer, scales: &GpuBuffer, out_dim: usize, nblk: usize, device: u32,
 ) -> Tensor {
     let in_dim = nblk * 32;
-    let out = Tensor::empty(&[in_dim, out_dim], DType::BF16, Device::Cuda(device));
+    // PROBE: zeros (not empty) to test for an uninitialized-read/coverage bug.
+    let out = Tensor::zeros(&[in_dim, out_dim], DType::BF16, Device::Cuda(device));
     unsafe {
         launch_mxfp4_dequant_bf16(
             blocks.as_ptr() as *const c_void,