Align DeepSeek and GLM execution with DS4

tools/sampler-replay-benchmark.rs

@@ -0,0 +1,39 @@
+// CPU-only diagnostic shared by the standalone DS4 oracle and Rust tests.
+// The input is the existing 32-row, little-endian F32 logit recording.
+pub fn run(
+    path: &std::path::Path,
+    vocab: usize,
+    mut sample: impl FnMut(&[f32]) -> i32,
+) -> Result<serde_json::Value, String> {
+    if !(1..=1_000_000).contains(&vocab) {
+        return Err("invalid sampler vocabulary size".into());
+    }
+    let expected = 32 * vocab * 4;
+    if std::fs::metadata(path).map_err(|e| e.to_string())?.len() != expected as u64 {
+        return Err("sampler recording must contain exactly 32 F32 rows".into());
+    }
+    let bytes = std::fs::read(path).map_err(|e| e.to_string())?;
+    if bytes.len() != expected {
+        return Err("sampler recording changed while reading".into());
+    }
+    let values = bytes
+        .chunks_exact(4)
+        .map(|b| f32::from_le_bytes(b.try_into().unwrap()))
+        .collect::<Vec<_>>();
+    for row in values.chunks_exact(vocab) {
+        std::hint::black_box(sample(row));
+    }
+    let mut batch_ms = Vec::with_capacity(16);
+    let mut token_ids = Vec::with_capacity(512);
+    for _ in 0..16 {
+        let started = std::time::Instant::now();
+        for row in values.chunks_exact(vocab) {
+            token_ids.push(std::hint::black_box(sample(row)));
+        }
+        batch_ms.push(started.elapsed().as_secs_f64() * 1000.0);
+    }
+    Ok(serde_json::json!({
+        "event":"sampler_replay_benchmark", "vocab":vocab, "rows":32,
+        "warmup_draws":32, "draws":512, "batch_ms":batch_ms, "token_ids":token_ids,
+    }))
+}