moe: fix decode correctness — zero dequant output (was uninitialized-read)

The KV-cache decode produced wrong, non-deterministic logits. Root cause:
dequant_mxfp4 allocated its output with Tensor::empty (uninitialized) and,
under MoE's heavy allocator churn, some output elements were read as
stale/garbage before use — deterministic in isolation (mxfp4-check) but not
in the full MoE path, where each run saw different dirty buffers. Allocating
the output with Tensor::zeros makes decode correct AND deterministic.

Verified (gptoss-logits, "The capital of France is"):
  forward top-1 = 12650 " Paris" 15.5625
  decode  top-1 = 12650 " Paris" 15.5625   MATCH_TOP1: YES
  3/3 identical decode runs.
gptoss-gen first generated token = 12650 " Paris" at ~9.5 tok/s, single 5090.

(Zeroing is a correct fix but also masks a possible coverage gap in the
dequant kernel; the kernel's per-thread index math looks complete, so this
is likely a stale-read hazard. Revisit if perf needs the memset gone.)

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,