docs(cookbook): add Qwen3.8-27B DGX Spark configs (#35121)

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

docs/cookbook/autoregressive/Qwen/Qwen3.8-27B.mdx

@@ -59,7 +59,10 @@ import { Qwen38MambaRatioCalculator } from "/src/snippets/_qwen38_mamba_ratio_ca
 <Note>
   The RTX 5090 and RTX PRO 6000 cells above — including every Speculative
   Decoding / Serving Strategy / SSM dtype combination — were validated at
-  ISL 8192 / OSL 1024, concurrency 1. The other platforms' recipes carry their
+  ISL 8192 / OSL 1024, concurrency 1. The DGX Spark cells cover that same full
+  combination set, but to a weaker standard: each was confirmed to **boot and
+  serve** at ISL 8192 / OSL 1024, concurrency 1, with no throughput or
+  acceptance-length numbers taken. The remaining platforms' recipes carry their
   original validation, which covers the default overlay picks (plus MTP on
   GB300); non-default overlay picks there are valid but unmeasured.
 </Note>
@@ -179,9 +182,17 @@ checkpoint's calibration scales automatically.
   requires a FlashInfer build whose prefill `plan` accepts `uniform_q_len`
   (newer than 0.6.15.post1); otherwise run spec with `--attention-backend triton`.
   On DGX Spark the 128GB is unified memory shared with the host CPU, so all
-  three checkpoints fit; its cells use 8192-token prefill chunks,
+  three checkpoints fit, and its cells reuse the RTX PRO 6000 recipe verbatim
-  `--mem-fraction-static 0.95`, and `--disable-prefill-cuda-graph`. The SM121
+  rather than a separate operating point. **Validated on SM121 / aarch64**: all
-  recipe is not yet validated on that platform.
+  36 configurations (3 checkpoints x Speculative Decoding x Serving Strategy x
+  Mamba SSM Dtype) booted and served on GB10 under `lmsysorg/sglang:qwen38-27b`
+  at ISL 8192 / OSL 1024, concurrency 1. That is boot-and-serve coverage only —
+  no throughput or acceptance-length numbers — and it includes the FlashInfer `plan` /
+  `uniform_q_len` path above, which raised no arity error on that image. Two
+  host quirks when reproducing on GB10: docker GPU access is CDI-only
+  (`--device nvidia.com/gpu=all`, as no `nvidia` runtime is registered), and
+  `nvidia-smi` reports `Not Supported` for memory because it is unified with the
+  CPU — gate a relaunch on `MemAvailable` in `/proc/meminfo` instead.
 - **H200 (SM90)**: BF16 and FP8 only — the card has no FP4 tensor cores, so the
   NVFP4 checkpoint's MLP would fall back to the Marlin W4A16 weight-only path
   and its cell is greyed out. The H200 recipes use 32768-token prefill chunks
@@ -238,8 +249,7 @@ checkpoint's calibration scales automatically.
 - `--chunked-prefill-size 2048`: decode steps stall behind each prefill chunk
   on hybrid GDN models, and 8192-token chunks stall them ~600ms at a time.
   2048 keeps decode inter-token latency smooth under mixed load and also
-  improves single-wave TTFT. (DGX Spark is the exception: its cells run
+  improves single-wave TTFT.
-  8192-token chunks.)
 
 ## 3. Agent Harnesses
 

docs/src/snippets/configs/Qwen/qwen3.8-27b.jsx

@@ -338,8 +338,9 @@ export const config = {
   // Verification: RTX 5090 / RTX PRO 6000 cells were measured across their
   // whole overlay envelope; the h200/gb300 badges carry the source page's
   // validation, which covers the overlay defaults (plus plain MTP on gb300) —
-  // non-default overlay picks there are valid but unmeasured. DGX Spark stays
+  // non-default overlay picks there are valid but unmeasured. DGX Spark was
-  // unverified (SM121 / aarch64 unvalidated).
+  // measured across its whole overlay envelope too, but to a weaker standard
+  // (boot-and-serve only — see the cell block comment below).
   //
   // Cells carry NO --mamba-full-memory-ratio: the ratio depends on workload,
   // S, D and kv_bytes_per_token, so the page's calculator computes it live
@@ -480,21 +481,30 @@ export const config = {
     },
     // DGX Spark (GB10, SM121): single node, 128GB coherent unified memory
     // shared with the CPU — every checkpoint fits, so all three quants get a
-    // cell. FlashInfer attention comes from the SM120 pair; the platform gets
+    // cell. These cells reuse the RTX PRO 6000 recipe verbatim rather than a
-    // its own operating point at 8192-token prefill chunks, 0.95 static
+    // separate SM121 operating point: both cards are SM12x Blackwell, and
-    // fraction, and prefill CUDA graphs disabled. Unvalidated on SM121 /
+    // GB10's 128GB unified pool is larger than the 6000's 96GB, so a recipe
-    // aarch64.
+    // that fits the smaller card has headroom here.
+    //
+    // Validated on GB10 (SM121 / aarch64): all 36 configurations booted and
+    // served at ISL 8192 / OSL 1024, concurrency 1. Boot-and-serve only -- no
+    // throughput or acceptance-length numbers were taken, so this is a weaker
+    // standard than the SM120 pair's validation, and the Deploy-panel Note says
+    // so.
     {
       match: { hw: "dgx-spark", variant: "default", quant: "nvfp4", nodes: "single" },
+      // All 12 overlay combinations served on GB10. DSPARK here also
+      // exercises the 4-bit `lm_head` this checkpoint quantizes, with no shape
+      // error.
+      verified: true,
       env: [],
       flags: [
         "--trust-remote-code",
         "--model-path {{MODEL_NAME}}",
         "--kv-cache-dtype fp8_e4m3",
-        "--mem-fraction-static 0.95",
+        "--mem-fraction-static 0.85",
         "--attention-backend flashinfer",
-        "--chunked-prefill-size 8192",
+        "--chunked-prefill-size 2048",
-        "--disable-prefill-cuda-graph",
         "--reasoning-parser qwen3",
         "--tool-call-parser qwen3_coder",
         "--host {{HOST_IP}}",
@@ -503,15 +513,16 @@ export const config = {
     },
     {
       match: { hw: "dgx-spark", variant: "default", quant: "fp8", nodes: "single" },
+      // All 12 overlay combinations served on GB10.
+      verified: true,
       env: [],
       flags: [
         "--trust-remote-code",
         "--model-path {{MODEL_NAME}}",
         "--kv-cache-dtype fp8_e4m3",
-        "--mem-fraction-static 0.95",
+        "--mem-fraction-static 0.85",
         "--attention-backend flashinfer",
-        "--chunked-prefill-size 8192",
+        "--chunked-prefill-size 2048",
-        "--disable-prefill-cuda-graph",
         "--reasoning-parser qwen3",
         "--tool-call-parser qwen3_coder",
         "--host {{HOST_IP}}",
@@ -520,15 +531,17 @@ export const config = {
     },
     {
       match: { hw: "dgx-spark", variant: "default", quant: "bf16", nodes: "single" },
+      // All 12 overlay combinations served on GB10. Heaviest checkpoint, so
+      // it holds the sweep's tightest cell: DSPARK + float32 + extra_buffer.
+      verified: true,
       env: [],
       flags: [
         "--trust-remote-code",
         "--model-path {{MODEL_NAME}}",
         "--kv-cache-dtype fp8_e4m3",
-        "--mem-fraction-static 0.95",
+        "--mem-fraction-static 0.85",
         "--attention-backend flashinfer",
-        "--chunked-prefill-size 8192",
+        "--chunked-prefill-size 2048",
-        "--disable-prefill-cuda-graph",
         "--reasoning-parser qwen3",
         "--tool-call-parser qwen3_coder",
         "--host {{HOST_IP}}",