[docs] Add DFlash2 speculative cells to the Qwen3.8-27B cookbook (#35663)

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

@@ -59,8 +59,12 @@ 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 DGX Spark cells cover that same full
+  ISL 8192 / OSL 1024, concurrency 1 — for DFLASH2, to that full standard on
-  combination set, but to a weaker standard: each was confirmed to **boot and
+  NVFP4, and to boot-and-serve on the RTX PRO 6000 BF16/FP8 cells. On the
+  remaining platforms the DFLASH2 pick is offered but not yet exercised, and
+  the composed command carries a `# DFLASH2 on this platform: final
+  verification in progress` hint line while it is selected. The DGX Spark cells cover that same combination set minus
+  DFLASH2, 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
@@ -89,7 +93,8 @@ ratio = (S + D) x state_bytes / (L x kv_bytes_per_token)
   slot, and `extra_buffer` frees one more with the overlap scheduler off; the
   calculator reads both knobs.
 - `D` — verify intermediate states under speculative decoding:
-  `--speculative-num-draft-tokens` for EAGLE/MTP (4 at the recommended 3/1/4);
+  `--speculative-num-draft-tokens` for EAGLE/MTP (4 at the recommended 3/1/4)
+  and for DFLASH (8, DFlash2's block size);
   `--speculative-dspark-block-size + 1` for DSPARK, where the block size falls
   back to the draft checkpoint's `block_size` when the flag is omitted (7 for
   `RadixArk/Qwen3.8-27B-DSpark`, so `D = 8`); 0 with speculation off or with
@@ -220,6 +225,29 @@ checkpoint's calibration scales automatically.
   `--enable-linear-replayssm-spec` its draft intermediates move onto a fixed
   ring, so `D = 0` and the ratio returns to the no-spec value. The
   [calculator](#mamba-ratio-calculator) applies both rules.
+- **DFlash2**: a trained block-diffusion draft in a separate checkpoint — add
+  `--speculative-algorithm DFLASH --speculative-draft-model-path
+  incoai/Qwen3.8-27B-DFlash2 --speculative-num-draft-tokens 8` (8 is the
+  draft's block size, and it is the `D` term in the ratio, same value as
+  DSpark's). The selector projects candidates through the target `lm_head`,
+  including quantized heads, so it runs on the NVFP4 checkpoint (whose head
+  is NVFP4-packed; the BF16 and FP8 checkpoints keep a dense head).
+  Validation: NVFP4 measured end-to-end on RTX PRO 6000 and RTX 5090; the
+  RTX PRO 6000 BF16/FP8 cells boot and serve; on H200, DGX Spark and GB300
+  the pick is offered with a final-verification-in-progress hint line
+  above the command. The
+  RTX PRO 6000 recipe needs no changes. On the 32GB RTX 5090 prefer
+  `--mamba-ssm-dtype bfloat16` at `--mem-fraction-static 0.90`: measured
+  strictly better than float32 for this draft (6.1 vs 8.3 ms TPOT, accept
+  3.30 vs 3.09) — the opposite of the EAGLE trade, so measure before assuming.
+  float32 still fits, but only at `--mem-fraction-static 0.945` with
+  `--mamba-full-memory-ratio 10` pinned in place of the balanced value: the
+  L = 9216 ratio leaves the fp32 state pool one slot short at every
+  serviceable mem-fraction (0.94 allocates four of Low-Latency's five slots;
+  0.95 OOMs at runtime), and the re-weighted split leaves the Low-Latency KV
+  pool a single-request envelope (~9.4k tokens) — no headroom for longer
+  requests or radix reuse. The panel's DFLASH2 option applies these re-pins
+  automatically.
 - **Hardware fit**: FP8 weights ~28.5GB (not serviceable beyond bs≤2 on
   32GB cards); NVFP4 weights ~16.5GB (recommended for RTX 5090-class GPUs).
 - `--mamba-radix-cache-strategy extra_buffer_lazy` lowers the state cost per

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

@@ -116,6 +116,49 @@ export const config = {
               : []),
           ],
         },
+        {
+          id: "dflash", label: "DFLASH2",
+          // Trained block-diffusion draft, a separate checkpoint. The
+          // selector projects through the target lm_head — including
+          // quantized heads — so it runs on the NVFP4 checkpoint too.
+          // Validated on the SM120 pair (NVFP4 measured end to end; the
+          // RTX PRO 6000 BF16/FP8 cells boot-and-serve). On the other
+          // platforms the pick is offered with the in-progress hint below
+          // — the recipe composes from validated cells but has not been
+          // exercised there yet.
+          disabled: (sel) => sel.hw === "rtx5090" && sel.quant !== "nvfp4",
+          disableReason:
+            "On the 32GB RTX 5090 the DFlash2 draft model only fits on top of the NVFP4 weights",
+          hints: (sel) =>
+            ["rtx6000", "rtx5090"].includes(sel.hw)
+              ? []
+              : ["DFLASH2 on this platform: final verification in progress"],
+          // 5090: mem-fraction re-pins like DSPARK's, and fp32 additionally
+          // re-pins the ratio — the balanced L=9216 value leaves the state
+          // pool one slot short at every serviceable mem-fraction (see the
+          // DFlash2 bullet in Configuration Tips).
+          stripPrefixes: (sel) =>
+            sel.hw === "rtx5090"
+              ? sel.ssmDtype === "float32"
+                ? ["--mem-fraction-static", "--mamba-full-memory-ratio"]
+                : ["--mem-fraction-static"]
+              : [],
+          flags: (sel) => [
+            "--speculative-algorithm DFLASH",
+            "--speculative-draft-model-path incoai/Qwen3.8-27B-DFlash2",
+            "--speculative-num-draft-tokens 8",
+            // Measured on the 5090: bf16 state serves at 0.90 (DSPARK's
+            // pin); fp32 fits only at 0.945 + ratio 10 (0.94 is one state
+            // slot short, 0.95 OOMs at runtime) and leaves the Low-Latency
+            // KV pool a single-request envelope.
+            ...(sel.hw === "rtx5090"
+              ? sel.ssmDtype === "float32"
+                ? ["--mem-fraction-static 0.945",
+                   "--mamba-full-memory-ratio 10"]
+                : ["--mem-fraction-static 0.90"]
+              : []),
+          ],
+        },
       ],
     },
     {
@@ -260,6 +303,11 @@ export const config = {
           flags: ["--speculative-algorithm DSPARK",
                   "--speculative-draft-model-path RadixArk/Qwen3.8-27B-DSpark",
                   "--speculative-draft-attention-backend flashinfer"] },
+        { id: "dflash",  label: "DFlash2",
+          // Same trio as the Deploy panel's DFLASH2 option.
+          flags: ["--speculative-algorithm DFLASH",
+                  "--speculative-draft-model-path incoai/Qwen3.8-27B-DFlash2",
+                  "--speculative-num-draft-tokens 8"] },
       ],
     },