review cleanups: pp+gpt-oss guard, sparse GEMV asserts, warnings

- --pp with gpt-oss now fails with a clear message instead of a
  cryptic missing-weight panic inside the Qwen3-only PP engine.
- Sparse GEMV wrappers assert K%16==0 (FP8) / K%32==0 (MXFP4) — the
  uint4-vectorized kernels would silently drop a tail otherwise.
- Document the topk_ids buffer holding i32 under an F32 dtype label
  (DType has no I32).
- Drop unused imports/locals and the cuBLASLt scale-mode constants
  orphaned by the strided-batched FP8 rework (e631a71).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

crates/xserv-kernels/src/embedding.rs

@@ -1,5 +1,4 @@
 use std::ffi::c_void;
-use xserv_cuda::GpuBuffer;
 use xserv_tensor::{DType, Device, Tensor};
 
 unsafe extern "C" {

crates/xserv-kernels/src/moe.rs

@@ -1,5 +1,5 @@
 use std::ffi::c_void;
-use xserv_tensor::{DType, Device, Tensor};
+use xserv_tensor::{DType, Tensor};
 
 use crate::gemm::{cublas_handle, CublasHandle};
 
@@ -88,6 +88,9 @@ pub fn moe_topk_softmax(
     let num_tokens = router_logits.shape()[0];
     assert_eq!(router_logits.shape()[1], num_experts);
 
+    // NOTE: topk_ids actually holds i32 expert indices; DType has no I32, so
+    // this is a raw 4-byte buffer mislabeled F32. Never read it as floats —
+    // all consumers (weighted-sum / sparse GEMV kernels) cast to int*.
     let topk_ids = Tensor::empty(&[num_tokens, top_k], DType::F32, router_logits.device());
     let topk_weights = Tensor::empty(&[num_tokens, top_k], DType::F32, router_logits.device());
 
@@ -201,8 +204,12 @@ pub fn moe_sparse_gemv_fp8(
 ) -> Tensor {
     assert_eq!(x.dtype(), DType::BF16);
     assert!(x.is_contiguous());
+    assert_eq!(w_fp8_t.dtype(), DType::FP8E4M3);
     let n = w_fp8_t.shape()[1];
     let k = w_fp8_t.shape()[2];
+    // The kernel reads weights as uint4 (16 FP8 values per lane) and would
+    // silently skip a K%16 tail.
+    assert_eq!(k % 16, 0, "sparse FP8 GEMV requires K % 16 == 0, got {k}");
     assert_eq!(x.shape()[x.ndim() - 1], k);
     assert_eq!(x.shape()[0], if x_per_slot { num_tokens * top_k } else { num_tokens });
 
@@ -233,6 +240,8 @@ pub fn moe_sparse_gemv_mxfp4(
 ) -> Tensor {
     assert_eq!(x.dtype(), DType::BF16);
     assert!(x.is_contiguous());
+    // 32-element MXFP4 blocks, read as uint4 (32 nibbles) per lane.
+    assert_eq!(k % 32, 0, "sparse MXFP4 GEMV requires K % 32 == 0, got {k}");
     assert_eq!(x.shape()[x.ndim() - 1], k);
     assert_eq!(x.shape()[0], if x_per_slot { num_tokens * top_k } else { num_tokens });
 

crates/xserv-kernels/src/quantization.rs

@@ -107,17 +107,11 @@ const CUDA_R_8F_E4M3: i32 = 28;
 // MatmulDesc attributes
 const CUBLASLT_MATMUL_DESC_A_SCALE_POINTER: i32 = 17;
 const CUBLASLT_MATMUL_DESC_B_SCALE_POINTER: i32 = 18;
-const CUBLASLT_MATMUL_DESC_A_SCALE_MODE: i32 = 31;
-const CUBLASLT_MATMUL_DESC_B_SCALE_MODE: i32 = 32;
 
 // MatrixLayout attributes
 const CUBLASLT_MATRIX_LAYOUT_BATCH_COUNT: i32 = 5;
 const CUBLASLT_MATRIX_LAYOUT_STRIDED_BATCH_OFFSET: i32 = 6;
 
-// Scale modes
-const CUBLASLT_MATMUL_MATRIX_SCALE_SCALAR: i32 = 0;
-const CUBLASLT_MATMUL_MATRIX_SCALE_OUTER_VEC_32F: i32 = 3;
-
 // MatmulPreference attributes
 const CUBLASLT_MATMUL_PREF_MAX_WORKSPACE_BYTES: i32 = 1;