docs(cookbook): re-benchmark DeepSeek-V4 on sglang 0.5.15 (#31363)

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>

.claude/skills/cookbook-add-model/templates/benchmarks.jsx.tmpl

@@ -7,7 +7,8 @@
 // "pending" until an entry has a non-null speed metric or accuracy. Speed shape:
 //   speed: [{ workload: {dataset, isl, osl, max_concurrency}, ttft_ms, tpot_ms,
 //             tokens_per_sec_per_gpu }, ...]
-//   - ttft_ms/tpot_ms are P50 (median); set config.latencyPercentile ("P50" default, or "Mean").
+//   - ttft_ms/tpot_ms are P50 (median); set config.latencyPercentile ("P50" default, or "Mean");
+//     an entry-level latencyPercentile overrides the page value per cell.
 //   - tokens_per_sec_per_gpu = total (in+out) tok/s/GPU
 //     (= output tok/s ÷ GPUs × (isl+osl)/osl). interactivity is derived = 1000/TPOT (tokens/s/user).
 // Per-cell `accuracy: { <key>: <pct> }` overrides the config's defaultAccuracy.

.claude/skills/cookbook-add-model/templates/config.jsx.tmpl

@@ -97,7 +97,8 @@ export const config = {
   --model {{MODEL_NAME}} \\
   --dataset-name {{DATASET}} \\
   --random-input-len {{ISL}} --random-output-len {{OSL}} \\
-  --num-prompts {{NUM_PROMPTS}} --max-concurrency {{MAX_CONCURRENCY}}`,
+  --num-prompts {{NUM_PROMPTS}} --max-concurrency {{MAX_CONCURRENCY}} \\
+  --flush-cache`,
     // One entry per accuracy field. A value is a string, OR a {[variant]: string}
     // object when the command differs per variant. Keys must match ACCURACY_LABELS
     // in _deployment.jsx + the per-cell/defaultAccuracy keys.