docs(specs): GLM-5.3-Flash three-way quant benchmark on ds4 (measured)

lab 89/100 @ 28.4 t/s (c1) / 43.4 (c2, MTP k=3); redhat 90/100 but 13.9 t/s
zero-MTP dead-end; LibertAIDAI 88/100, k=5 MTP regresses under c2.
All served under one stable name glm53. Includes boot markers, ops notes
(occupancy race after stop, transient first-launch death, reasoning-effort
smoke-test pitfall) and follow-ups.

specs/tech-architecture/glm53-recipe-state.md

@@ -0,0 +1,72 @@
+# GLM-5.3-Flash NVFP4 — three quant variants measured on 2× DGX Spark (ds4)
+
+Measured 2026-08-27/28 on cluster `ds4` (dgx3+dgx4, switched fabric), all three
+served by sm121 through the launcher, same benchmark invocation:
+
+```
+tool-eval-bench run --base-url http://<head>:30000/v1 --model glm53 \
+  --seed 42 --hardmode --perf --concurrency 1,2
+```
+
+All three share served name **`glm53`** — clients never changed between runs.
+
+## Results
+
+| recipe | quant | quality | points | decode tg t/s (c1) | tg c2 | TTFT | deployability | MTP |
+|---|---|---|---|---|---|---|---|---|
+| `glm53-flash-nvfp4-lab` | local-inference-lab mixed NVFP4/MXFP8-MTP | **89** | 155/174 | **28.4** | **43.4** | 3.9 s | 70 | ✅ k=3, accept len ~2.9–3.5, ~63–83 % |
+| `glm53-flash-nvfp4-redhat` | RedHatAI W4A4 compressed-tensors | **90** | 159/176 | 13.9 | 13.8 | 2.2 s | 67 | ❌ (no MTP weights in checkpoint) |
+| `glm53-flash-nvfp4` | LibertAIDAI NVFP4-A16 | **88** | 154/176 | 26.2 | 22.7 | 6.3 s | 69 | ✅ k=5 |
+
+(lab scored /174 — one scenario skipped by the harness that run; quality % is
+comparable. LibertAIDAI is the only variant whose MTP *regresses* under c2
+(26.2→22.7) — lab's k=3 draft scales, LibertAIDAI's k=5 does not.)
+
+Prefill (pp2048) 0.3–1.7 K t/s depending on depth/concurrency — noisy, all three
+in the same band (NAS load-influenced); decode is the stable discriminator.
+
+## Read of the numbers
+
+- **lab** is the throughput pick: MTP doubles decode (28–43 t/s vs ~14 baseline)
+  at −1 quality point. Acceptance lengths matched upstream's 2.55–3.5 range.
+- **redhat** is the quality pick (90/100 — best of the three) but is a
+  **baseline-decode dead-end on this box: its checkpoint ships zero MTP tensors**
+  (verified index: 146,745 tensors, none under layer 45), so it is stuck at ~14 t/s.
+- **lab = best agent-throughput/day-driver; redhat = eval ceiling;
+  LibertAIDAI = solid fallback** (proven first, but k=5 MTP regresses at c2).
+
+## Images & patches
+
+| image dir | base | patches |
+|---|---|---|
+| `glm53-flash-nvfp4` | vllm/vllm-openai:glm53-flash-arm64-cu130 | kingjones30 NoPE-MLA mod (4-part, anchor-asserted) |
+| `glm53-flash-nvfp4-lab` | same | + 4 FujitsuPolycom patches (Apache-2.0, see patches/UPSTREAM.md): model.py naming shim, modelopt MTP namespace fix, persistent_topk CC-12.x guards ×2 |
+| redhat recipe reuses `glm53-flash-nvfp4:local` (mod is quant-independent) | | |
+
+Boot markers `[quantprobe] layer=RoutedExperts prefix=model.layers.45.mlp.experts
+algo=MXFP8` confirm the MTP fix is live; `algo=None` there = broken load.
+
+## Operational notes (measured)
+
+- lab weight load: 92.19 GiB / 700 s sequential from the NAS HF cache;
+  `--kv-cache-memory-bytes 10737418240` → KV 1,164,369 tokens / 2.22× @ 512K
+  (matches upstream to the digit — do NOT switch back to GMU sizing).
+- First launcher serve of lab died on both ranks at ~54 s (exit 1, logs lost
+  to `--rm`); re-run was clean twice. Suspected transient (cold imports +
+  simultaneous launch). If it recurs: re-launch without `--rm` and keep logs.
+- `sm121 serve` immediately after `sm121 stop` can fail with "cluster has only
+  1 nodes" — occupancy race, nodes not yet released; wait ~10 s and retry.
+- LibertAIDAI/redhat recipes still run FlashInfer autotune (60-min possible
+  boot, `VLLM_ENGINE_READY_TIMEOUT_S=3600` set); the lab recipe disables it via
+  `--kernel-config` per upstream's proven boot.
+- Chat-template caveat: `reasoning_effort:"low"` still emits a reasoning trace
+  (budget ≠ 0); `max_tokens:48` can yield `content: null, finish: length` —
+  use ≥256 for smoke tests.
+
+## Follow-ups
+
+- Vendor instanttensor loader into the lab image (~30 s vs 700 s weight load).
+- Consider adding `--kernel-config` autotune-off + pinned KV to the redhat and
+  LibertAIDAI recipes (their boot could be minutes shorter; verify before trusting).
+- MTP for redhat is impossible unless someone trains/exports a drafter into
+  the checkpoint — don't chase it.