[Docs] DeepSeek-V4 cookbook: drop --disable-flashinfer-autotune from GB300 Flash low-latency (#28590)

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

docs_new/src/snippets/configs/deepseek-ai/deepseek-v4-benchmarks.jsx

@@ -140,6 +140,13 @@ export const benchmarks = [
   // ====================================================================
   {
     match: { hw: "gb300", variant: "flash", quant: "fp4", strategy: "low-latency", nodes: "single" },
+    sglang_version: "0.5.13.post1",
+    speed: [
+      { workload: { dataset: "random", isl: 8192, osl: 1024, max_concurrency: 1 },
+        ttft_ms: 463, tpot_ms: 4.19, tokens_per_sec_per_gpu: 35 },
+      { workload: { dataset: "random", isl: 8192, osl: 1024, max_concurrency: 16 },
+        ttft_ms: 436, tpot_ms: 8.93, tokens_per_sec_per_gpu: 336 },
+    ],
   },
   {
     match: { hw: "gb300", variant: "flash", quant: "fp4", strategy: "balanced", nodes: "single" },

docs_new/src/snippets/configs/deepseek-ai/deepseek-v4.jsx

@@ -743,7 +743,6 @@ sgl-eval run aime25 \\
         "--speculative-eagle-topk 1",
         "--speculative-num-draft-tokens 4",
         "--chunked-prefill-size 4096",
-        "--disable-flashinfer-autotune",
         "--swa-full-tokens-ratio 0.1",
         "--host {{HOST_IP}}",
         "--port {{PORT}}",