[cookbook] add inkling dspark command (#32465)

Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>

docs_new/cookbook/autoregressive/ThinkingMachines/Inkling.mdx

@@ -37,6 +37,7 @@ There are two multi-arch (amd64 / arm64) CUDA builds plus a ROCm build; pick the
 docker pull lmsysorg/sglang:inkling-cu13            # CUDA 13
 docker pull lmsysorg/sglang:inkling-cu12            # CUDA 12
 docker pull lmsysorg/sglang:inkling-rocm700-mi35x   # AMD MI350X / MI355X
+docker pull lmsysorg/sglang:dev-cu13-inkling-dspark # CUDA 13 + DSpark support
 ```
 
 For how to launch the image, see [Install → Method 3: Using Docker](../../../docs/get-started/install#method-3-using-docker). Substitute the inner `sglang serve ...` with what the command generator below produces.
@@ -47,7 +48,7 @@ For how to launch the image, see [Install → Method 3: Using Docker](../../../d
 
 </Accordion>
 
-Pick your hardware to generate the launch command. Each platform ships a **Balanced** recipe plus an **MTP** (speculative decoding) tier and a **Long Context (MXFP8 KV)** tier where validated; the **LoRA** variant serves adapters on top of the frozen base model. Set `MAX_LORAS` to the number of distinct adapters you serve (1 is fastest for single-adapter serving).
+Pick your hardware to generate the launch command. Each platform ships a **Balanced** recipe plus **MTP** and **DSpark** (speculative decoding) tiers and a **Long Context (MXFP8 KV)** tier where validated; the **LoRA** variant serves adapters on top of the frozen base model. Set `MAX_LORAS` to the number of distinct adapters you serve (1 is fastest for single-adapter serving).
 
 import { Deployment } from "/src/snippets/_deployment.jsx";
 import { config }     from "/src/snippets/configs/thinkingmachines/inkling.jsx";
@@ -301,3 +302,9 @@ The **Long Context** deploy strategy adds `--kv-cache-dtype mxfp8` on top of the
 The tradeoff is not just a ~5% decode latency penalty from the extra quantize/dequantize work versus BF16 KV — storing KV in MXFP8 also introduces some accuracy loss at long context lengths. Treat it as a capacity lever, not a speed one — stay on **Balanced** if you have headroom in the memory pool and just want lower latency or maximum output quality.
 
 To try it, select the **Long Context** strategy in the Deploy panel above for any NVFP4 cell; the panel regenerates the launch command with `--kv-cache-dtype mxfp8` inserted. Verified end-to-end on B200, B300, and GB300.
+
+### 3.7 DSpark (Speculative Decoding)
+
+The **DSpark** deploy strategy is the second speculative-decoding path for Inkling. Unlike **MTP**, which drives Inkling's own multi-layer draft head, DSpark runs a **separate draft checkpoint** — `RadixArk/Inkling-DSpark-Preview` — served unquantized alongside the NVFP4 target.
+
+It needs an SGLang build with DSpark support — `lmsysorg/sglang:dev-cu13-inkling-dspark`, which the Deploy panel's **Docker** command uses for this tier; the `inkling-cu13` / `inkling-cu12` images don't carry DSpark yet. Verified end-to-end on B200 (TP=8, NVFP4).

docs_new/src/snippets/_deployment.jsx

@@ -51,8 +51,9 @@
 //                      override the page value per cell (entry → config → "P50").
 //                      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|quant`
+//   dockerImages       optional — `docker run` image, keyed by
-//                      then `hw`; falls back to `lmsysorg/sglang:dev`
+//                      `hw|quant|strategy` then `hw|quant` then `hw`;
+//                      falls back to `lmsysorg/sglang:dev`
 //   runModes           optional — command output tabs to show (`python` and/or
 //                      `docker`); defaults to both, in that order
 //   github             optional — "Submit verified cell" issue-template overrides
@@ -674,9 +675,12 @@ export const Deployment = ({ config, benchmarks }) => {
 
     let cmd;
     if (mode === "docker") {
-      // Image keyed by `hw|quant` (most specific) then `hw`; `:dev` if unmapped.
+      // 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).
       const di = config.dockerImages || {};
-      const image = di[`${sel.hw}|${sel.quant}`] || di[sel.hw] || "lmsysorg/sglang:dev";
+      const image = di[`${sel.hw}|${sel.quant}|${sel.strategy}`]
+        || di[`${sel.hw}|${sel.quant}`] || di[sel.hw] || "lmsysorg/sglang:dev";
       const portFlag = flags.find((x) => x.split(/[\s=]/)[0] === "--port");
       const servePort = portFlag ? portFlag.slice("--port".length).trim() : "{{PORT}}";
       const vendorOf = (hwId) => {

docs_new/src/snippets/_playground.jsx

@@ -1365,9 +1365,14 @@ export const Playground = ({ config }) => {
     }
     let cmd;
     if (mode === "docker") {
-      // Image keyed by `hw|quant` (most specific) then `hw`; `:dev` if unmapped (matches _deployment.jsx).
+      // 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.
       const di = config.dockerImages || {};
-      const image = di[`${sel.hw}|${sel.quant}`] || di[sel.hw] || "lmsysorg/sglang:dev";
+      const image = di[`${sel.hw}|${sel.quant}|${sel.strategy}`]
+        || di[`${sel.hw}|${sel.quant}`] || di[sel.hw] || "lmsysorg/sglang:dev";
       const portFlag = f.find((x) => x.split(/[\s=]/)[0] === "--port");
       const servePort = portFlag ? portFlag.slice("--port".length).trim() : "{{PORT}}";
       const dockerLines = [

docs_new/src/snippets/configs/thinkingmachines/inkling-benchmarks.jsx

@@ -32,6 +32,7 @@ export const benchmarks = [
   { match: { hw: "gb200"  , variant: "default" , quant: "nvfp4" , strategy: "mtp"          , nodes: "single"   } },
   { match: { hw: "gb300"  , variant: "default" , quant: "nvfp4" , strategy: "mtp"          , nodes: "single"   } },
   { match: { hw: "h200"   , variant: "default" , quant: "nvfp4" , strategy: "mtp"          , nodes: "single"   } },
+  { match: { hw: "b200"   , variant: "default" , quant: "nvfp4" , strategy: "dspark"       , nodes: "single"   } },
   { match: { hw: "b200"   , variant: "default" , quant: "nvfp4" , strategy: "long_context" , nodes: "single"   } },
   { match: { hw: "b300"   , variant: "default" , quant: "nvfp4" , strategy: "long_context" , nodes: "single"   } },
   { match: { hw: "gb200"  , variant: "default" , quant: "nvfp4" , strategy: "long_context" , nodes: "single"   } },

docs_new/src/snippets/configs/thinkingmachines/inkling.jsx

@@ -26,6 +26,7 @@ export const config = {
   strategies: [
     { id: "balanced",     label: "Balanced"                  },
     { id: "mtp",          label: "MTP"                        },
+    { id: "dspark",       label: "DSpark"                     },
     { id: "long_context", label: "Long Context (MXFP8 KV)"    },
   ],
   nodesOptions: [
@@ -73,7 +74,10 @@ export const config = {
 
   // NVIDIA: two multi-arch CUDA builds (inkling-cu12 / inkling-cu13) — pick by your
   // CUDA version, not by GPU. AMD: inkling-rocm700-mi35x. Panel defaults to cu13.
+  // The DSpark tier needs its own preview build (DSpark isn't in the inkling-cu1x
+  // images yet), so it takes a `hw|quant|strategy` key.
   dockerImages: {
+    "b200|nvfp4|dspark": "lmsysorg/sglang:dev-cu13-inkling-dspark",
     h200:  "lmsysorg/sglang:inkling-cu13",
     b200:  "lmsysorg/sglang:inkling-cu13",
     b300:  "lmsysorg/sglang:inkling-cu13",
@@ -682,6 +686,49 @@ export const config = {
         "--port {{PORT}}",
       ],
     },
+    // ====================================================================
+    // DSpark (speculative decoding) — separate draft checkpoint
+    // (RadixArk/Inkling-DSpark-Preview, served unquantized) instead of Inkling's
+    // own MTP head, so it needs a build carrying DSpark support: the
+    // `dev-cu13-inkling-dspark` image (see the dockerImages key above).
+    // The draft weights sit outside the FP4 target, hence mem-fraction 0.68.
+    // B200 verified end-to-end.
+    // ====================================================================
+    {
+      match: { hw: "b200", variant: "default", quant: "nvfp4", strategy: "dspark", nodes: "single" },
+      verified: true,
+      env: [
+        "SGLANG_ENABLE_UNIFIED_RADIX_TREE=1",
+      ],
+      flags: [
+        "--trust-remote-code",
+        "--model-path {{MODEL_NAME}}",
+        "--tp 8",
+        "--quantization modelopt_fp4",
+        "--attention-backend fa4",
+        "--page-size 128",
+        "--fp4-gemm-backend flashinfer_trtllm",
+        "--moe-runner-backend flashinfer_trtllm_routed",
+        "--enable-torch-symm-mem",
+        "--mamba-radix-cache-strategy extra_buffer",
+        "--mem-fraction-static 0.68",
+        "--swa-full-tokens-ratio 0.1",
+        "--mamba-full-memory-ratio 0.1",
+        "--max-running-requests 68",
+        "--reasoning-parser inkling",
+        "--tool-call-parser inkling",
+        "--skip-server-warmup",
+        "--speculative-algorithm DSPARK",
+        "--speculative-draft-model-path RadixArk/Inkling-DSpark-Preview",
+        "--speculative-draft-model-quantization unquant",
+        "--chunked-prefill-size 8192",
+        "--cuda-graph-max-bs-prefill 8192",
+        "--disable-flashinfer-autotune",
+        "--host {{HOST_IP}}",
+        "--port {{PORT}}",
+      ],
+    },
+
     // ====================================================================
     // GB300 BF16 — 2x GB300 nodes (4 GPUs each) over MNNVL. The NCCL_MNNVL /
     // NVLS / CUMEM envs are required: 2-node NCCL init hangs without them.