Explorar el Código

ledger: glm53-flash-aiden-4x row (89/156-176, 37.6 tg c1 flat to d8192, prefill 2,185 = his ref) + TC-43 note

Alexander Korolev hace 1 mes
padre
commit
509654fbed
Se han modificado 1 ficheros con 6 adiciones y 1 borrados
  1. 6 1
      specs/tech-architecture/glm53-recipe-state.md

+ 6 - 1
specs/tech-architecture/glm53-recipe-state.md

@@ -18,6 +18,7 @@ All three share served name **`glm53`** — clients never changed between runs.
 | `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 |
 | `glm53-flash-nvfp4-4p67` | 4p67 W4A16-experts + MXFP8-attn, eager, MTP k=3 | **87** | 153/176 | 24.4 | 39.2 | 1.4 s | 67 | ✅ accept ~90% |
+| `glm53-flash-aiden-4x` | aiden image production-1.1 (DFlash2 overlay), NVFP4, **incoai DFlash2 k=7**, eager, 16 GiB KV pin, 4× Spark TP4 (his production shape) | **89** | 156/176 | 37.6 (d0 c1; flat to d8192, 2,185 pp t/s — matches his ~2,100) | 50.7 (c2) / 63.5 (c4) | 0.9 s | **80** | ✅ DFlash2 k=7 |
 | `glm53-flash-aiden-2x` | aiden image **production-1.1** (DFlash2 overlay), NVFP4, **incoai DFlash2 k=7**, eager, 4 GiB KV pin (2x profile) | **89** | 157/176 | 22.3 (d0 c1; d8192 c4 degrades — 4 GiB pin) | — | — | 66 | ✅ DFlash2 k=7 (drafter block 8−1) |
 | `glm53-flash-sparkrun` | community sparkrun image (aidendle94), NVFP4, eager, NO MTP (image lacks the fix) | **89** | 154/176 | 14.3 | 23.8 | 1.4 s | 66 | ❌ (n/a in image) |
 | `glm53-flash-exl3` | brandonmusic EXL3/TR3 4bpw (Entrpi image + instanttensor), DFlash2-7, graphs | **88** | 155/176 | 23.1 | 24.1 | 2.6 s d0 | **77** | ✅ accept 48–81 % |
@@ -27,7 +28,11 @@ failure (one trial crossed the 120 s request timeout; the scenario runs ~140 s
 total — harness drops timed-out scenarios from the denominator; had it scored
 like redhat's 2/2, lab would be 157/176 = 89 — no change). 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.)
+(26.2→22.7) — lab's k=3 draft scales, LibertAIDAI's k=5 does not.
+
+4x note (2026-09-04): the 4x aiden run had one safety-critical failure —
+TC-43 called `web_search` with an empty query (required-parameter violation);
+not seen in the 2x aiden run.)
 
 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.