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-server/src/main.rs

@@ -65,6 +65,13 @@ async fn main() {
         std::process::exit(1);
     }
     let model_config = ModelConfig::from_file(&model_dir.join("config.json"));
+    // gpt-oss is only implemented in the TP engine; route it there even at
+    // tp=1 (single-rank world) so quantized models can serve on one GPU.
+    let is_gpt_oss = model_config.model_type.as_deref() == Some("gpt_oss");
+    if pp > 1 && is_gpt_oss {
+        eprintln!("gpt-oss is not supported by the pipeline-parallel engine (Qwen3 only); use --tp instead");
+        std::process::exit(1);
+    }
     let model_max_seq_len = model_config.max_seq_len();
     if model_max_seq_len == 0 {
         eprintln!("model config has invalid max_seq_len=0");
@@ -87,9 +94,6 @@ async fn main() {
     let (tx, rx) = mpsc::channel::<GenerateRequest>();
 
     let model_dir_clone = model_dir.clone();
-    // gpt-oss is only implemented in the TP engine; route it there even at
-    // tp=1 (single-rank world) so quantized models can serve on one GPU.
-    let is_gpt_oss = model_config.model_type.as_deref() == Some("gpt_oss");
     std::thread::spawn(move || {
         if pp > 1 {
             // Pipeline-parallel path: stage-0 coordinator + worker stage threads.