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-model/src/gpt2.rs

@@ -199,7 +199,7 @@ impl GPT2 {
         layer: &GPT2Block,
         x: &Tensor,
         cache: Option<(&mut KVCache, usize)>,
-        pos_offset: usize,
+        _pos_offset: usize,
         new_tokens: usize,
         num_heads: usize,
         head_dim: usize,

crates/xserv-model/src/kv_cache.rs

@@ -1,5 +1,5 @@
 use xserv_cuda::GpuBuffer;
-use xserv_tensor::{DType, Device, Tensor};
+use xserv_tensor::{DType, Tensor};
 use crate::config::ModelConfig;
 
 /// GPU-resident KV cache. Pre-allocates max_seq_len on GPU,

crates/xserv-model/src/qwen3.rs

@@ -1,7 +1,7 @@
 use std::collections::HashMap;
 use half::bf16;
 use xserv_kernels::*;
-use xserv_tensor::{DType, Device, Tensor};
+use xserv_tensor::{Device, Tensor};
 
 use crate::config::ModelConfig;
 use crate::gpt2::KVCache;
@@ -798,7 +798,7 @@ impl Qwen3 {
     pub fn forward_gpu_cache(&self, token_ids: &[u32], cache: &mut GpuKVCache) -> Tensor {
         let new_tokens = token_ids.len();
         let pos_offset = cache.seq_len();
-        let hidden = self.config.hidden();
+
         let num_heads = self.config.num_heads();
         let num_kv_heads = self.config.num_kv_heads();
         let head_dim = self.config.head_dim();