model: fused GPU MoE kernel — eliminate CPU roundtrip

Replace the per-token CPU-routed MoE forward with an all-GPU path:

  1. moe_topk_softmax: GPU top-k + softmax (was CPU sort + softmax)
  2. moe_replicate: broadcast input to all local experts
  3. cublasGemmStridedBatchedEx: batched expert matmul (was per-expert cuBLAS)
  4. moe_weighted_sum: FP32-accumulated weighted sum on GPU (was GPU→CPU→F32→BF16→GPU)

Expert weights stored as contiguous 3D tensors for strided batched GEMM.
Zero CPU↔GPU transfers per MoE layer (was ~40 per token per layer).

Also: configurable geglu_alpha, LayerNorm bias auto-detect, unused-weight
diagnostic at load time.

GSM8K 30-problem: 11/30 → 23/30 (76.7%) vs llama.cpp 30/30 (100%).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

crates/xserv-model/src/config.rs

@@ -73,6 +73,10 @@ pub struct ModelConfig {
     pub rope_scaling: Option<RopeScaling>,
     #[serde(default)]
     pub swiglu_limit: Option<f64>,
+    #[serde(default)]
+    pub geglu_alpha: Option<f64>,
+    #[serde(default)]
+    pub hidden_act: Option<String>,
 }
 
 impl ModelConfig {
@@ -144,4 +148,8 @@ impl ModelConfig {
     pub fn window_size(&self) -> usize {
         self.sliding_window.unwrap_or(0)
     }
+
+    pub fn geglu_alpha(&self) -> f32 {
+        self.geglu_alpha.unwrap_or(1.702) as f32
+    }
 }