From 6d34a4d3ce1005593fdb89478651ded47c0d5277 Mon Sep 17 00:00:00 2001
From: zijiexia <37504505+zijiexia@users.noreply.github.com>
Date: Tue, 1 Sep 2026 17:11:41 -0700
Subject: [PATCH] [Cookbook] Verify DeepSeek-V4 Flash Vision on GB300 (#37492)

---
 .../deepseek-ai/deepseek-v4-benchmarks.jsx    | 23 +++++++++++++++----
 .../configs/deepseek-ai/deepseek-v4.jsx       | 12 ++++------
 2 files changed, 24 insertions(+), 11 deletions(-)

diff --git a/docs/src/snippets/configs/deepseek-ai/deepseek-v4-benchmarks.jsx b/docs/src/snippets/configs/deepseek-ai/deepseek-v4-benchmarks.jsx
index 4580c90f6..67bb983fc 100644
--- a/docs/src/snippets/configs/deepseek-ai/deepseek-v4-benchmarks.jsx
+++ b/docs/src/snippets/configs/deepseek-ai/deepseek-v4-benchmarks.jsx
@@ -665,16 +665,31 @@ export const benchmarks = [
     accuracy: { mmmu_pro_pct: 73.76 },
     notes: "MMMU-Pro (standard, 10-option) measured with sgl-eval on 4×B200 (TP=4, DP=4, MegaMoE) at temperature 1.0, top-p 0.95, --reasoning-effort max; target-only (DP Attention is incompatible with DSpark).",
   },
-  // B300 / GB200 / GB300 / H200 / H100 — Flash Vision (Exp), all pending
+  // B300 / GB200 / H200 / H100 — Flash Vision (Exp), all pending
   { match: { hw: "b300", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" } },
   { match: { hw: "b300", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" } },
   { match: { hw: "b300", variant: "flash-vision", quant: "fp4", strategy: "high-throughput", nodes: "single" } },
   { match: { hw: "gb200", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" } },
   { match: { hw: "gb200", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" } },
   { match: { hw: "gb200", variant: "flash-vision", quant: "fp4", strategy: "high-throughput", nodes: "single" } },
-  { match: { hw: "gb300", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" } },
-  { match: { hw: "gb300", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" } },
-  { match: { hw: "gb300", variant: "flash-vision", quant: "fp4", strategy: "high-throughput", nodes: "single" } },
+  {
+    match: { hw: "gb300", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" },
+    sglang_version: "PR #37253 @ 61f962c",
+    accuracy: { mmmu_pro_pct: 74.10 },
+    notes: "MMMU-Pro (standard, 10-option) measured with sgl-eval on 4×GB300 (TP=4) at temperature 1.0, top-p 0.95, --reasoning-effort max, with the bundled DSpark head enabled (--speculative-algorithm DSPARK).",
+  },
+  {
+    match: { hw: "gb300", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" },
+    sglang_version: "PR #37253 @ 61f962c",
+    accuracy: { mmmu_pro_pct: 73.41 },
+    notes: "MMMU-Pro (standard, 10-option) measured with sgl-eval on 4×GB300 (TP=4, DP=4, DeepEP) at temperature 1.0, top-p 0.95, --reasoning-effort max; target-only (DP Attention is incompatible with DSpark).",
+  },
+  {
+    match: { hw: "gb300", variant: "flash-vision", quant: "fp4", strategy: "high-throughput", nodes: "single" },
+    sglang_version: "PR #37253 @ 61f962c",
+    accuracy: { mmmu_pro_pct: 74.57 },
+    notes: "MMMU-Pro (standard, 10-option) measured with sgl-eval on 4×GB300 (TP=4, DP=4, MegaMoE) at temperature 1.0, top-p 0.95, --reasoning-effort max; target-only (DP Attention is incompatible with DSpark).",
+  },
   { match: { hw: "h200", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" } },
   { match: { hw: "h200", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" } },
   { match: { hw: "h100", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" } },
diff --git a/docs/src/snippets/configs/deepseek-ai/deepseek-v4.jsx b/docs/src/snippets/configs/deepseek-ai/deepseek-v4.jsx
index 1afa2c99a..f5fb6a542 100644
--- a/docs/src/snippets/configs/deepseek-ai/deepseek-v4.jsx
+++ b/docs/src/snippets/configs/deepseek-ai/deepseek-v4.jsx
@@ -3083,7 +3083,8 @@ sgl-eval run mmmu_pro \\
     // verified on B200 via the MMMU-Pro round (4×B200, image batches).
     // Balanced / high-throughput stay target-only: those recipes run DP
     // attention, which DSpark is incompatible with on the current release.
-    // Non-B200 hardware — final verification in progress.
+    // GB300 verified via the same MMMU-Pro round (4×GB300); B300 /
+    // GB200 / H200 / H100 — final verification in progress.
     // ====================================================================
     {
       match: { hw: "b200", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" },
@@ -3244,8 +3245,7 @@ sgl-eval run mmmu_pro \\
     },
     {
       match: { hw: "gb300", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" },
-      verified: false,
-      verificationStatus: "in-progress",
+      verified: true,
       warn: "DeepSeek-V4-Flash-Vision-Exp support has not shipped in an SGLang release yet (sglang PR 37253): Docker mode already points at the preview image; for Python mode install SGLang from that PR. See [Flash Vision notes](#vision-note).",
       env: [],
       flags: [
@@ -3259,8 +3259,7 @@ sgl-eval run mmmu_pro \\
     },
     {
       match: { hw: "gb300", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" },
-      verified: false,
-      verificationStatus: "in-progress",
+      verified: true,
       warn: "DeepSeek-V4-Flash-Vision-Exp support has not shipped in an SGLang release yet (sglang PR 37253): Docker mode already points at the preview image; for Python mode install SGLang from that PR. See [Flash Vision notes](#vision-note).",
       env: ["SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=1024"],
       flags: [
@@ -3277,8 +3276,7 @@ sgl-eval run mmmu_pro \\
     },
     {
       match: { hw: "gb300", variant: "flash-vision", quant: "fp4", strategy: "high-throughput", nodes: "single" },
-      verified: false,
-      verificationStatus: "in-progress",
+      verified: true,
       warn: "DeepSeek-V4-Flash-Vision-Exp support has not shipped in an SGLang release yet (sglang PR 37253): Docker mode already points at the preview image; for Python mode install SGLang from that PR. See [Flash Vision notes](#vision-note).",
       env: [
         "SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK=8320",