[Cookbook] Add DeepSeek-V4-Flash-Vision-Exp to the DeepSeek-V4 page (#37293)

docs/src/snippets/_deployment.jsx

@@ -80,6 +80,7 @@
 //                      Legacy "Mean" data is being re-measured to P50; drop once done
 //   multiNodeHints     optional — {[hwId]: string[]} prepended as `# ...` lines
 //   dockerImages       optional — `docker run` image, keyed by
+//                      `hw|variant|quant` then `variant|quant` then
 //                      `hw|quant|strategy` then `hw|quant` then `hw`;
 //                      falls back to `lmsysorg/sglang:dev`
 //   dockerHostNetworkWhen optional — `(selection, {flags, env}) => boolean`
@@ -780,11 +781,15 @@ export const Deployment = ({ config, benchmarks }) => {
 
     let cmd;
     if (mode === "docker") {
-      // Image keyed by `hw|quant|strategy` (most specific), then `hw|quant`,
-      // then `hw`; `:dev` if unmapped. The strategy key covers a tier that
-      // needs its own build (e.g. a spec-decoding preview image).
+      // Image keyed by `hw|variant|quant` (most specific), then `variant|quant`,
+      // then `hw|quant|strategy`, `hw|quant`, `hw`; `:dev` if unmapped. The
+      // variant keys cover a checkpoint that needs its own build (e.g. a
+      // new-variant preview image); the strategy key covers a tier that needs
+      // one (e.g. a spec-decoding preview image).
       const di = config.dockerImages || {};
-      const image = di[`${sel.hw}|${sel.quant}|${sel.strategy}`]
+      const image = di[`${sel.hw}|${sel.variant}|${sel.quant}`]
+        || di[`${sel.variant}|${sel.quant}`]
+        || di[`${sel.hw}|${sel.quant}|${sel.strategy}`]
         || di[`${sel.hw}|${sel.quant}`] || di[sel.hw] || "lmsysorg/sglang:dev";
       const dockerRunCommand = typeof config.dockerRunCommand === "function"
         ? config.dockerRunCommand(sel)

docs/src/snippets/_playground.jsx

@@ -1520,13 +1520,17 @@ export const Playground = ({ config }) => {
     }
     let cmd;
     if (mode === "docker") {
-      // Image keyed by `hw|quant|strategy` (most specific), then `hw|quant`, then
-      // `hw`; `:dev` if unmapped (matches _deployment.jsx). The strategy key covers
-      // a tier that needs its own build (e.g. a spec-decoding preview image), so the
-      // playground base must resolve it too or it hands back an image that cannot
-      // run the command.
+      // Image keyed by `hw|variant|quant` (most specific), then `variant|quant`,
+      // then `hw|quant|strategy`, `hw|quant`, `hw`; `:dev` if unmapped (matches
+      // _deployment.jsx). The variant keys cover a checkpoint that needs its own
+      // build (e.g. a new-variant preview image) and the strategy key a tier that
+      // needs one (e.g. a spec-decoding preview image), so the playground base
+      // must resolve them too or it hands back an image that cannot run the
+      // command.
       const di = config.dockerImages || {};
-      const image = di[`${sel.hw}|${sel.quant}|${sel.strategy}`]
+      const image = di[`${sel.hw}|${sel.variant}|${sel.quant}`]
+        || di[`${sel.variant}|${sel.quant}`]
+        || di[`${sel.hw}|${sel.quant}|${sel.strategy}`]
         || di[`${sel.hw}|${sel.quant}`] || di[sel.hw] || "lmsysorg/sglang:dev";
       const dockerRunCommand = typeof config.dockerRunCommand === "function"
         ? config.dockerRunCommand(sel)

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

@@ -634,4 +634,28 @@ export const benchmarks = [
   { match: { hw: "mi355x", variant: "pro", quant: "fp8", strategy: "low-latency", nodes: "single" } },
   { match: { hw: "mi355x", variant: "pro", quant: "fp8", strategy: "balanced", nodes: "single" } },
   { match: { hw: "mi355x", variant: "pro", quant: "fp8", strategy: "high-throughput", nodes: "single" } },
+  // ====================================================================
+  // B200 + FP4 — Flash Vision (Exp)
+  // ====================================================================
+  {
+    match: { hw: "b200", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" },
+    sglang_version: "dev-dsv4-flash-vision",
+    accuracy: { mmmu_pro_pct: 74.96 },
+    notes: "MMMU-Pro (standard, 10-option) measured with sgl-eval on 4×B200 (TP=4) at temperature 1.0, top-p 0.95, --reasoning-effort max.",
+  },
+  { match: { hw: "b200", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" } },
+  { match: { hw: "b200", variant: "flash-vision", quant: "fp4", strategy: "high-throughput", nodes: "single" } },
+  // B300 / GB200 / GB300 / 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: "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" } },
 ];

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

@@ -25,6 +25,7 @@ export const config = {
   variants: [
     { id: "flash", label: "Flash", subtitle: "284B" },
     { id: "flash-official", label: "Flash Official", subtitle: "284B · 0731" },
+    { id: "flash-vision", label: "Flash Vision", subtitle: "305B · Exp" },
     { id: "pro",   label: "Pro",   subtitle: "1.6T" },
     { id: "pro-official", label: "Pro Official", subtitle: "1.6T · 0813" },
   ],
@@ -49,6 +50,7 @@ export const config = {
     "flash|fp8": "deepseek-ai/DeepSeek-V4-Flash",
     "flash|nvfp4": "nvidia/DeepSeek-V4-Flash-NVFP4",
     "flash-official|fp4": "deepseek-ai/DeepSeek-V4-Flash-0731",
+    "flash-vision|fp4": "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
     "pro|fp4":   "deepseek-ai/DeepSeek-V4-Pro",
     "pro|fp8":   "deepseek-ai/DeepSeek-V4-Pro",
     "pro|nvfp4": "nvidia/DeepSeek-V4-Pro-NVFP4",
@@ -144,6 +146,14 @@ sgl-eval run aime25 \\
   --n-repeats 16 --max-tokens 400000 \\
   --temperature 1.0 --top-p 1.0 --thinking \\
   --out-dir /sgl-workspace/logs \\
+  --base-url http://{{CURL_HOST}}:{{CURL_PORT}}/v1`,
+      },
+      mmmu_pro_pct: {
+        "flash-vision":
+`# To install sgl-eval: pip install git+https://github.com/sgl-project/sgl-eval
+sgl-eval run mmmu_pro \\
+  --reasoning-effort max \\
+  --temperature 1.0 --top-p 0.95 \\
   --base-url http://{{CURL_HOST}}:{{CURL_PORT}}/v1`,
       },
     },
@@ -162,6 +172,7 @@ sgl-eval run aime25 \\
     ["gpqa_pct",   "GPQA Diamond",   "%"],
     ["aime25_pct", "AIME25",         "%"],
     ["gsm8k_pct",  "GSM8K (1-shot)", "%"],
+    ["mmmu_pro_pct", "MMMU-Pro (standard, 10-option)", "%"],
   ],
 
   // Prepended as `# ...` comments above multi-node commands.
@@ -175,6 +186,10 @@ sgl-eval run aime25 \\
   },
 
   dockerImages: {
+    // Flash Vision (Exp) support has not shipped in a release yet
+    // (sgl-project/sglang#37253) — until it does, the variant needs this
+    // preview build on every hardware.
+    "flash-vision|fp4": "lmsysorg/sglang:dev-dsv4-flash-vision",
     h100:  "lmsysorg/sglang:latest",
     h200:  "lmsysorg/sglang:latest",
     b200:  "lmsysorg/sglang:latest",
@@ -289,15 +304,17 @@ sgl-eval run aime25 \\
         { id: "mtp-314",    label: "EAGLE / MTP 3-1-4",
           flags: ["--speculative-algorithm EAGLE", "--speculative-num-steps 3",
                   "--speculative-eagle-topk 1", "--speculative-num-draft-tokens 4"],
-          hide: { variant: ["flash-official", "pro-official"] } },
+          hide: { variant: ["flash-official", "flash-vision", "pro-official"] } },
         { id: "mtp-112",    label: "EAGLE / MTP 1-1-2",
           flags: ["--speculative-algorithm EAGLE", "--speculative-num-steps 1",
                   "--speculative-eagle-topk 1", "--speculative-num-draft-tokens 2"],
-          hide: { variant: ["flash-official", "pro-official"] } },
+          hide: { variant: ["flash-official", "flash-vision", "pro-official"] } },
         { id: "dspark",     label: "DSpark",
           flags: ["--speculative-algorithm DSPARK"],
           hide: { variant: ["flash", "pro"] },
           disable: [
+            { when: { variant: ["flash-vision"] },
+              reason: "The Flash Vision checkpoint bundles a DSpark head, but speculative decoding is not yet verified with image inputs — the cookbook recipes run target-only for now." },
             { when: { dpAttnOn: [true] },
               reason: "DSpark is not compatible with DP Attention on the current release." },
             { when: { hw: ["mi300x", "mi355x"] },
@@ -2826,5 +2843,277 @@ sgl-eval run aime25 \\
         "--port {{PORT}}",
       ],
     },
+
+    // ====================================================================
+    // B200 + FP4 — Flash Vision (Exp)
+    //
+    // DeepSeek-V4-Flash-Vision-Exp (sgl-project/sglang#37253): the 0731
+    // Flash base plus a vision encoder + aligner. The checkpoint bundles a
+    // DSpark head, but speculative decoding is not yet verified with image
+    // batches, so every recipe runs target-only. Low-latency is the serving
+    // shape the MMMU-Pro round ran on (4×B200); balanced / high-throughput
+    // mirror the Flash Official recipes on the same 4-GPU topology — final
+    // verification in progress.
+    // ====================================================================
+    {
+      match: { hw: "b200", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" },
+      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: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--mem-fraction-static 0.85",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+    {
+      match: { hw: "b200", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--dp 4",
+        "--enable-dp-attention",
+        "--moe-a2a-backend deepep",
+        "--mem-fraction-static 0.85",
+        "--deepep-config '{\"normal_dispatch\":{\"num_sms\":96},\"normal_combine\":{\"num_sms\":96}}'",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+    {
+      match: { hw: "b200", variant: "flash-vision", quant: "fp4", strategy: "high-throughput", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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",
+      ],
+      flags: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--dp 4",
+        "--enable-dp-attention",
+        "--moe-a2a-backend megamoe",
+        "--mem-fraction-static 0.85",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+
+    // ====================================================================
+    // B300 / GB200 / GB300 + FP4 — Flash Vision (Exp)
+    // ====================================================================
+    {
+      match: { hw: "b300", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--mem-fraction-static 0.85",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+    {
+      match: { hw: "b300", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--dp 4",
+        "--enable-dp-attention",
+        "--moe-a2a-backend deepep",
+        "--mem-fraction-static 0.85",
+        "--deepep-config '{\"normal_dispatch\":{\"num_sms\":96},\"normal_combine\":{\"num_sms\":96}}'",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+    {
+      match: { hw: "b300", variant: "flash-vision", quant: "fp4", strategy: "high-throughput", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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",
+      ],
+      flags: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--dp 4",
+        "--enable-dp-attention",
+        "--moe-a2a-backend megamoe",
+        "--mem-fraction-static 0.85",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+    {
+      match: { hw: "gb200", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--mem-fraction-static 0.85",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+    {
+      match: { hw: "gb200", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--dp 4",
+        "--enable-dp-attention",
+        "--moe-a2a-backend deepep",
+        "--mem-fraction-static 0.85",
+        "--deepep-config '{\"normal_dispatch\":{\"num_sms\":96},\"normal_combine\":{\"num_sms\":96}}'",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+    {
+      match: { hw: "gb200", variant: "flash-vision", quant: "fp4", strategy: "high-throughput", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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",
+      ],
+      flags: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--dp 4",
+        "--enable-dp-attention",
+        "--moe-a2a-backend megamoe",
+        "--mem-fraction-static 0.85",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+    {
+      match: { hw: "gb300", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--mem-fraction-static 0.85",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+    {
+      match: { hw: "gb300", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--dp 4",
+        "--enable-dp-attention",
+        "--moe-a2a-backend deepep",
+        "--mem-fraction-static 0.85",
+        "--deepep-config '{\"normal_dispatch\":{\"num_sms\":96},\"normal_combine\":{\"num_sms\":96}}'",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+    {
+      match: { hw: "gb300", variant: "flash-vision", quant: "fp4", strategy: "high-throughput", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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",
+      ],
+      flags: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--dp 4",
+        "--enable-dp-attention",
+        "--moe-a2a-backend megamoe",
+        "--mem-fraction-static 0.85",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+
+    // ====================================================================
+    // H200 + FP4 — Flash Vision (Exp)
+    // ====================================================================
+    {
+      match: { hw: "h200", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--moe-runner-backend marlin",
+        "--mem-fraction-static 0.85",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+    {
+      match: { hw: "h200", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 4",
+        "--moe-runner-backend flashinfer_mxfp4",
+        "--mem-fraction-static 0.85",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+
+    // ====================================================================
+    // H100 + FP4 — Flash Vision (Exp)
+    // ====================================================================
+    {
+      match: { hw: "h100", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" },
+      verified: false,
+      verificationStatus: "in-progress",
+      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: [
+        "--model-path {{MODEL_NAME}}",
+        "--tp 8",
+        "--moe-runner-backend marlin",
+        "--mem-fraction-static 0.85",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
   ],
 };