archive auto-beta0p05: eval.log
Browse files- arms/auto-beta0p05/eval.log +1099 -0
arms/auto-beta0p05/eval.log
ADDED
|
@@ -0,0 +1,1099 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[decode] loading /home/patrickd/models/DeepSeek-V4-Flash-0731-REAP ... s=6 NDEC=8 seqmax=297
|
| 2 |
+
[decode] loaded 100.40 GiB, 45821 tensors (weights in MANAGED device-preferred memory)
|
| 3 |
+
[decode] KV layout: fp32, 2048 B/row, 0.024 GiB for 297 rows x 43 layers
|
| 4 |
+
[decode] building 43 layer structs once (persistent)...
|
| 5 |
+
[decode] structs built. mem 108.5/122.8 GiB
|
| 6 |
+
[decode] prefill 5 positions...
|
| 7 |
+
[f32mk] tile 4x4 (DSV4_F32MK_TILE=unset)
|
| 8 |
+
[decode] PREFILL: 5 positions in 196.2 ms = 25.5 tok/s (39.237 ms/tok)
|
| 9 |
+
[decode] prefill done. caches populated. starting decode.
|
| 10 |
+
step 0 pos 5 -> token 11111 (67.7 ms warmup)
|
| 11 |
+
step 1 pos 6 -> token 16 (66.9 ms)
|
| 12 |
+
step 2 pos 7 -> token 455 (73.3 ms)
|
| 13 |
+
step 3 pos 8 -> token 6102 (66.7 ms)
|
| 14 |
+
step 4 pos 9 -> token 294 (67.3 ms)
|
| 15 |
+
step 5 pos 10 -> token 16603 (66.9 ms)
|
| 16 |
+
step 6 pos 11 -> token 344 (72.5 ms)
|
| 17 |
+
step 7 pos 12 -> token 29168 (66.3 ms)
|
| 18 |
+
|
| 19 |
+
[decode] first decoded token argmax = 11111 (expect 11111) -> GATE PASS
|
| 20 |
+
[decode] generated: 11111 16 455 6102 294 16603 344 29168
|
| 21 |
+
[decode] WARM decode: 68.6 ms/tok = 14.59 tok/s (M=1 steady state, 7-step avg)
|
| 22 |
+
|
| 23 |
+
[spec-verify] M=5 verify in ONE forward: 115.0 ms (= 23.0 ms/tok if all accepted vs 68.6 M=1 -> 2.98x)
|
| 24 |
+
[spec-verify] verify argmax: 11111 16 455 6102 294
|
| 25 |
+
[spec-verify] decode tokens: 11111 16 455 6102 294
|
| 26 |
+
[spec-verify] MATCH 5/5 -> PASS (M=K verify == K sequential decodes; diffs = MoE-atomic near-ties)
|
| 27 |
+
|
| 28 |
+
[spec] loading EXTERNAL DSpark head /home/patrickd/s5-capture/auto-beta0p05/head ...
|
| 29 |
+
[spec] head loaded 6.53 GiB, 2977 mtp tensors (SEPARATE store)
|
| 30 |
+
[spec] NSTAGE=3 head-experts=160 BLK sweep: 5 5 5 5 5 5 5 5 5
|
| 31 |
+
[spec] head built. mem 114.7/122.8 GiB
|
| 32 |
+
[decode] PREFILL: 5 positions in 137.9 ms = 36.3 tok/s (27.576 ms/tok)
|
| 33 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=0 s=6)...
|
| 34 |
+
[arena] first draft: draft footprint 210.72 MB, global hwm 210.72 MB / cap 512.00 MB (41.2%), draft path = ARENA
|
| 35 |
+
[margins] 1.78 1.27 0.59 0.55 0.73 K=2
|
| 36 |
+
verify 1: accepted 1/1 (K=2) + correction -> +2 tokens (97.7 ms) cpos=7
|
| 37 |
+
[margins] 0.40 1.25 0.33 0.24 0.12 K=2
|
| 38 |
+
verify 2: accepted 0/1 (K=2) + correction -> +1 tokens (102.9 ms) cpos=8
|
| 39 |
+
[margins] 1.47 0.95 1.82 0.19 0.02 K=2
|
| 40 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (96.1 ms) cpos=10
|
| 41 |
+
[margins] 2.41 0.35 3.92 0.46 1.38 K=2
|
| 42 |
+
verify 4: accepted 0/1 (K=2) + correction -> +1 tokens (98.6 ms) cpos=11
|
| 43 |
+
[margins] 6.50 0.04 0.47 1.69 2.49 K=2
|
| 44 |
+
verify 5: accepted 1/1 (K=2) + correction -> +2 tokens (99.3 ms) cpos=13
|
| 45 |
+
[margins] 4.27 2.74 5.19 2.16 0.56 K=5
|
| 46 |
+
verify 6: accepted 4/4 (K=5) + correction -> +5 tokens (139.0 ms) cpos=18
|
| 47 |
+
[margins] 5.11 2.59 2.07 0.74 0.97 K=4
|
| 48 |
+
verify 7: accepted 1/3 (K=4) + correction -> +2 tokens (125.9 ms) cpos=20
|
| 49 |
+
[margins] 2.48 2.20 5.09 2.24 2.02 K=6
|
| 50 |
+
verify 8: accepted 4/5 (K=6) + correction -> +5 tokens (154.9 ms) cpos=25
|
| 51 |
+
[margins] 7.11 2.12 2.00 3.19 2.72 K=6
|
| 52 |
+
verify 9: accepted 1/5 (K=6) + correction -> +2 tokens (156.5 ms) cpos=27
|
| 53 |
+
[margins] 3.65 3.44 6.11 2.64 0.58 K=5
|
| 54 |
+
verify 10: accepted 4/4 (K=5) + correction -> +5 tokens (144.2 ms) cpos=32
|
| 55 |
+
[margins] 7.22 0.10 3.64 1.81 1.36 K=2
|
| 56 |
+
verify 11: accepted 1/1 (K=2) + correction -> +2 tokens (95.9 ms) cpos=34
|
| 57 |
+
[margins] 2.08 4.13 4.98 1.61 1.25 K=5
|
| 58 |
+
verify 12: accepted 4/4 (K=5) + correction -> +5 tokens (141.2 ms) cpos=39
|
| 59 |
+
[margins] 4.58 0.04 4.53 2.87 3.30 K=2
|
| 60 |
+
verify 13: accepted 1/1 (K=2) + correction -> +2 tokens (100.8 ms) cpos=41
|
| 61 |
+
[margins] 3.48 3.71 6.25 1.63 0.95 K=5
|
| 62 |
+
verify 14: accepted 4/4 (K=5) + correction -> +5 tokens (140.1 ms) cpos=46
|
| 63 |
+
[margins] 1.71 1.31 4.51 0.36 3.39 K=2
|
| 64 |
+
verify 15: accepted 1/1 (K=2) + correction -> +2 tokens (100.9 ms) cpos=48
|
| 65 |
+
[margins] 0.04 0.63 1.05 1.62 0.59 K=2
|
| 66 |
+
verify 16: accepted 0/1 (K=2) + correction -> +1 tokens (97.9 ms) cpos=49
|
| 67 |
+
[margins] 6.54 4.74 3.67 5.07 1.17 K=5
|
| 68 |
+
verify 17: accepted 4/4 (K=5) + correction -> +5 tokens (143.5 ms) cpos=54
|
| 69 |
+
[margins] 2.99 1.81 7.06 0.20 2.48 K=4
|
| 70 |
+
verify 18: accepted 3/3 (K=4) + correction -> +4 tokens (127.1 ms) cpos=58
|
| 71 |
+
[margins] 1.15 5.07 5.46 6.35 1.40 K=5
|
| 72 |
+
verify 19: accepted 0/4 (K=5) + correction -> +1 tokens (141.5 ms) cpos=59
|
| 73 |
+
[margins] 5.86 6.07 6.88 0.12 5.17 K=4
|
| 74 |
+
verify 20: accepted 3/3 (K=4) + correction -> +4 tokens (129.2 ms) cpos=63
|
| 75 |
+
[margins] 0.59 0.99 6.98 0.98 3.68 K=2
|
| 76 |
+
verify 21: accepted 0/1 (K=2) + correction -> +1 tokens (101.5 ms) cpos=64
|
| 77 |
+
[margins] 6.40 0.39 3.23 2.63 3.85 K=2
|
| 78 |
+
verify 22: accepted 1/1 (K=2) + correction -> +2 tokens (98.3 ms) cpos=66
|
| 79 |
+
[margins] 4.65 4.25 5.10 2.71 0.10 K=5
|
| 80 |
+
verify 23: accepted 4/4 (K=5) + correction -> +5 tokens (142.4 ms) cpos=71
|
| 81 |
+
[margins] 6.75 1.83 2.17 1.43 2.09 K=4
|
| 82 |
+
verify 24: accepted 3/3 (K=4) + correction -> +4 tokens (129.8 ms) cpos=75
|
| 83 |
+
[margins] 7.30 5.32 2.92 0.67 0.99 K=4
|
| 84 |
+
verify 25: accepted 2/3 (K=4) + correction -> +3 tokens (128.1 ms) cpos=78
|
| 85 |
+
[margins] 6.03 0.43 1.75 5.10 3.03 K=2
|
| 86 |
+
verify 26: accepted 1/1 (K=2) + correction -> +2 tokens (103.6 ms) cpos=80
|
| 87 |
+
[margins] 5.10 6.46 5.84 3.61 1.82 K=6
|
| 88 |
+
verify 27: accepted 4/5 (K=6) + correction -> +5 tokens (160.1 ms) cpos=85
|
| 89 |
+
[margins] 7.77 0.97 2.77 3.74 3.69 K=2
|
| 90 |
+
verify 28: accepted 1/1 (K=2) + correction -> +2 tokens (99.4 ms) cpos=87
|
| 91 |
+
[margins] 5.87 5.72 7.38 2.59 2.67 K=6
|
| 92 |
+
verify 29: accepted 4/5 (K=6) + correction -> +5 tokens (166.1 ms) cpos=92
|
| 93 |
+
[margins] 7.98 1.08 0.03 3.31 5.27 K=2
|
| 94 |
+
verify 30: accepted 1/1 (K=2) + correction -> +2 tokens (100.8 ms) cpos=94
|
| 95 |
+
[margins] 4.94 4.93 4.79 3.42 2.61 K=6
|
| 96 |
+
verify 31: accepted 4/5 (K=6) + correction -> +5 tokens (167.3 ms) cpos=99
|
| 97 |
+
[margins] 5.87 1.64 0.79 3.02 4.38 K=3
|
| 98 |
+
verify 32: accepted 1/2 (K=3) + correction -> +2 tokens (117.8 ms) cpos=101
|
| 99 |
+
[margins] 6.95 5.88 6.01 0.06 1.39 K=4
|
| 100 |
+
verify 33: accepted 3/3 (K=4) + correction -> +4 tokens (130.5 ms) cpos=105
|
| 101 |
+
[margins] 2.14 7.57 0.40 6.10 3.82 K=3
|
| 102 |
+
verify 34: accepted 2/2 (K=3) + correction -> +3 tokens (117.6 ms) cpos=108
|
| 103 |
+
[margins] 6.94 4.68 6.05 3.08 2.20 K=6
|
| 104 |
+
verify 35: accepted 4/5 (K=6) + correction -> +5 tokens (162.3 ms) cpos=113
|
| 105 |
+
[margins] 8.08 1.57 0.14 3.90 3.20 K=3
|
| 106 |
+
verify 36: accepted 1/2 (K=3) + correction -> +2 tokens (116.9 ms) cpos=115
|
| 107 |
+
[margins] 3.51 1.96 7.10 2.70 0.24 K=5
|
| 108 |
+
verify 37: accepted 4/4 (K=5) + correction -> +5 tokens (149.7 ms) cpos=120
|
| 109 |
+
[margins] 7.49 1.61 0.73 3.65 1.69 K=3
|
| 110 |
+
verify 38: accepted 1/2 (K=3) + correction -> +2 tokens (113.6 ms) cpos=122
|
| 111 |
+
[margins] 6.05 4.28 5.85 4.61 1.27 K=5
|
| 112 |
+
verify 39: accepted 4/4 (K=5) + correction -> +5 tokens (145.3 ms) cpos=127
|
| 113 |
+
[margins] 7.76 1.47 0.85 4.04 4.62 K=2
|
| 114 |
+
verify 40: accepted 1/1 (K=2) + correction -> +2 tokens (119.6 ms) cpos=129
|
| 115 |
+
[margins] 8.14 6.31 8.32 1.67 1.67 K=6
|
| 116 |
+
verify 41: accepted 4/5 (K=6) + correction -> +5 tokens (163.2 ms) cpos=134
|
| 117 |
+
[margins] 6.72 1.50 1.15 2.16 2.92 K=2
|
| 118 |
+
verify 42: accepted 1/1 (K=2) + correction -> +2 tokens (107.3 ms) cpos=136
|
| 119 |
+
[margins] 7.96 4.12 5.14 2.70 1.59 K=6
|
| 120 |
+
verify 43: accepted 5/5 (K=6) + correction -> +6 tokens (161.9 ms) cpos=142
|
| 121 |
+
[margins] 9.05 9.01 2.81 2.13 5.57 K=6
|
| 122 |
+
verify 44: accepted 2/5 (K=6) + correction -> +3 tokens (165.4 ms) cpos=145
|
| 123 |
+
[margins] 6.76 6.16 7.15 1.85 2.30 K=6
|
| 124 |
+
verify 45: accepted 4/5 (K=6) + correction -> +5 tokens (160.1 ms) cpos=150
|
| 125 |
+
[margins] 7.17 1.11 1.79 5.62 4.95 K=2
|
| 126 |
+
verify 46: accepted 1/1 (K=2) + correction -> +2 tokens (105.5 ms) cpos=152
|
| 127 |
+
[margins] 14.20 3.06 7.80 7.91 9.52 K=6
|
| 128 |
+
verify 47: accepted 1/5 (K=6) + correction -> +2 tokens (161.5 ms) cpos=154
|
| 129 |
+
[margins] 3.84 8.79 7.62 4.40 3.45 K=6
|
| 130 |
+
verify 48: accepted 4/5 (K=6) + correction -> +5 tokens (166.6 ms) cpos=159
|
| 131 |
+
[margins] 3.64 0.03 0.07 4.58 4.72 K=2
|
| 132 |
+
verify 49: accepted 1/1 (K=2) + correction -> +2 tokens (105.0 ms) cpos=161
|
| 133 |
+
[margins] 9.60 6.63 7.90 7.66 3.30 K=6
|
| 134 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (163.3 ms) cpos=167
|
| 135 |
+
[margins] 6.10 1.08 2.41 4.54 4.70 K=2
|
| 136 |
+
verify 51: accepted 1/1 (K=2) + correction -> +2 tokens (104.6 ms) cpos=169
|
| 137 |
+
[margins] 2.68 5.00 6.46 3.71 2.40 K=6
|
| 138 |
+
verify 52: accepted 4/5 (K=6) + correction -> +5 tokens (160.5 ms) cpos=174
|
| 139 |
+
[margins] 3.77 1.89 1.30 4.66 5.84 K=3
|
| 140 |
+
verify 53: accepted 1/2 (K=3) + correction -> +2 tokens (117.3 ms) cpos=176
|
| 141 |
+
[margins] 4.47 5.67 6.88 2.45 1.00 K=5
|
| 142 |
+
verify 54: accepted 4/4 (K=5) + correction -> +5 tokens (144.5 ms) cpos=181
|
| 143 |
+
[margins] 7.00 2.12 0.10 2.06 6.08 K=3
|
| 144 |
+
verify 55: accepted 1/2 (K=3) + correction -> +2 tokens (118.0 ms) cpos=183
|
| 145 |
+
[margins] 3.98 6.39 8.25 2.56 0.80 K=5
|
| 146 |
+
verify 56: accepted 4/4 (K=5) + correction -> +5 tokens (150.7 ms) cpos=188
|
| 147 |
+
[margins] 2.18 0.48 1.23 1.02 6.36 K=2
|
| 148 |
+
verify 57: accepted 1/1 (K=2) + correction -> +2 tokens (102.1 ms) cpos=190
|
| 149 |
+
[margins] 9.29 2.10 0.10 3.20 2.63 K=3
|
| 150 |
+
verify 58: accepted 1/2 (K=3) + correction -> +2 tokens (118.4 ms) cpos=192
|
| 151 |
+
[margins] 6.37 2.54 6.50 6.31 8.64 K=6
|
| 152 |
+
verify 59: accepted 5/5 (K=6) + correction -> +6 tokens (162.3 ms) cpos=198
|
| 153 |
+
[margins] 1.49 6.37 0.71 1.36 4.14 K=3
|
| 154 |
+
verify 60: accepted 2/2 (K=3) + correction -> +3 tokens (119.1 ms) cpos=201
|
| 155 |
+
[margins] 5.93 7.40 8.64 7.61 1.16 K=5
|
| 156 |
+
verify 61: accepted 4/4 (K=5) + correction -> +5 tokens (144.9 ms) cpos=206
|
| 157 |
+
|
| 158 |
+
[spec] generated 201 tokens over 61 verifies: mean tokens/verify = 3.30 (block=5, max 6)
|
| 159 |
+
[spec] tokens: 11111 16 455 6102 294 16603 344 29168 16 455 6102 294 14251 344 16235 16 455 6102 294 29585 344 76405 16 455 6102 294 25062 344 40977 16 455 6102 294 10322 344 17575 16 455 6102 294
|
| 160 |
+
[spec] LOSSLESS GATE: first 8 tokens match base AR -> PASS
|
| 161 |
+
[spec] SPEC-DECODE: 39.2 ms/tok = 25.49 tok/s (vs base M=1 68.6 ms/tok = 14.59 tok/s -> 1.75x)
|
| 162 |
+
[decode] PREFILL: 34 positions in 602.5 ms = 56.4 tok/s (17.719 ms/tok)
|
| 163 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=1 s=35)...
|
| 164 |
+
[margins] 2.24 1.71 1.69 1.93 0.55 K=5
|
| 165 |
+
verify 1: accepted 0/4 (K=5) + correction -> +1 tokens (134.6 ms) cpos=35
|
| 166 |
+
[margins] 2.92 2.58 2.04 2.26 4.93 K=6
|
| 167 |
+
verify 2: accepted 0/5 (K=6) + correction -> +1 tokens (159.2 ms) cpos=36
|
| 168 |
+
[margins] 1.64 1.47 0.83 3.22 0.63 K=2
|
| 169 |
+
verify 3: accepted 0/1 (K=2) + correction -> +1 tokens (95.3 ms) cpos=37
|
| 170 |
+
[margins] 1.84 2.35 1.70 1.42 0.67 K=4
|
| 171 |
+
verify 4: accepted 2/3 (K=4) + correction -> +3 tokens (122.7 ms) cpos=40
|
| 172 |
+
[margins] 0.54 0.54 0.89 0.21 1.20 K=2
|
| 173 |
+
verify 5: accepted 0/1 (K=2) + correction -> +1 tokens (96.9 ms) cpos=41
|
| 174 |
+
[margins] 1.27 3.26 0.14 1.65 0.80 K=3
|
| 175 |
+
verify 6: accepted 2/2 (K=3) + correction -> +3 tokens (112.5 ms) cpos=44
|
| 176 |
+
[margins] 0.75 5.42 11.16 2.28 1.77 K=6
|
| 177 |
+
verify 7: accepted 5/5 (K=6) + correction -> +6 tokens (155.0 ms) cpos=50
|
| 178 |
+
[margins] 3.35 1.89 0.20 0.43 1.48 K=3
|
| 179 |
+
verify 8: accepted 1/2 (K=3) + correction -> +2 tokens (112.7 ms) cpos=52
|
| 180 |
+
[margins] 4.79 5.33 7.55 1.93 0.53 K=5
|
| 181 |
+
verify 9: accepted 3/4 (K=5) + correction -> +4 tokens (140.9 ms) cpos=56
|
| 182 |
+
[margins] 3.71 2.60 0.02 2.21 5.88 K=3
|
| 183 |
+
verify 10: accepted 2/2 (K=3) + correction -> +3 tokens (107.9 ms) cpos=59
|
| 184 |
+
[margins] 0.59 0.65 3.50 0.64 1.69 K=2
|
| 185 |
+
verify 11: accepted 0/1 (K=2) + correction -> +1 tokens (101.9 ms) cpos=60
|
| 186 |
+
[margins] 1.28 1.76 5.35 0.64 1.14 K=4
|
| 187 |
+
verify 12: accepted 0/3 (K=4) + correction -> +1 tokens (126.4 ms) cpos=61
|
| 188 |
+
[margins] 0.92 4.28 0.09 1.29 0.50 K=3
|
| 189 |
+
verify 13: accepted 1/2 (K=3) + correction -> +2 tokens (114.8 ms) cpos=63
|
| 190 |
+
[margins] 2.01 4.74 0.61 5.25 0.05 K=3
|
| 191 |
+
verify 14: accepted 0/2 (K=3) + correction -> +1 tokens (115.3 ms) cpos=64
|
| 192 |
+
[margins] 4.28 0.24 0.44 6.76 1.65 K=2
|
| 193 |
+
verify 15: accepted 1/1 (K=2) + correction -> +2 tokens (97.7 ms) cpos=66
|
| 194 |
+
[margins] 1.19 1.54 3.10 5.01 0.23 K=5
|
| 195 |
+
verify 16: accepted 4/4 (K=5) + correction -> +5 tokens (139.4 ms) cpos=71
|
| 196 |
+
[margins] 2.72 1.50 1.35 4.77 0.07 K=3
|
| 197 |
+
verify 17: accepted 2/2 (K=3) + correction -> +3 tokens (114.8 ms) cpos=74
|
| 198 |
+
[margins] 7.48 1.99 3.12 2.66 3.12 K=6
|
| 199 |
+
verify 18: accepted 5/5 (K=6) + correction -> +6 tokens (160.9 ms) cpos=80
|
| 200 |
+
[margins] 5.42 5.40 5.25 2.20 6.83 K=6
|
| 201 |
+
verify 19: accepted 5/5 (K=6) + correction -> +6 tokens (158.5 ms) cpos=86
|
| 202 |
+
[margins] 8.67 3.68 2.89 5.85 0.81 K=5
|
| 203 |
+
verify 20: accepted 4/4 (K=5) + correction -> +5 tokens (143.4 ms) cpos=91
|
| 204 |
+
[margins] 7.39 2.12 3.56 8.58 0.87 K=5
|
| 205 |
+
verify 21: accepted 4/4 (K=5) + correction -> +5 tokens (146.5 ms) cpos=96
|
| 206 |
+
[margins] 9.43 5.74 4.35 8.40 2.36 K=6
|
| 207 |
+
verify 22: accepted 5/5 (K=6) + correction -> +6 tokens (158.5 ms) cpos=102
|
| 208 |
+
[margins] 9.71 3.28 7.47 8.31 6.14 K=6
|
| 209 |
+
verify 23: accepted 5/5 (K=6) + correction -> +6 tokens (165.6 ms) cpos=108
|
| 210 |
+
[margins] 2.99 1.22 0.09 6.81 4.74 K=2
|
| 211 |
+
verify 24: accepted 0/1 (K=2) + correction -> +1 tokens (102.1 ms) cpos=109
|
| 212 |
+
[margins] 9.18 6.65 5.25 5.60 5.45 K=6
|
| 213 |
+
verify 25: accepted 5/5 (K=6) + correction -> +6 tokens (159.6 ms) cpos=115
|
| 214 |
+
[margins] 9.54 8.86 10.03 3.05 7.03 K=6
|
| 215 |
+
verify 26: accepted 5/5 (K=6) + correction -> +6 tokens (167.5 ms) cpos=121
|
| 216 |
+
[margins] 9.55 5.18 3.92 8.76 0.53 K=5
|
| 217 |
+
verify 27: accepted 4/4 (K=5) + correction -> +5 tokens (147.6 ms) cpos=126
|
| 218 |
+
[margins] 8.75 6.54 7.43 1.05 0.84 K=4
|
| 219 |
+
verify 28: accepted 3/3 (K=4) + correction -> +4 tokens (148.5 ms) cpos=130
|
| 220 |
+
[margins] 8.36 7.62 5.46 3.39 8.36 K=6
|
| 221 |
+
verify 29: accepted 5/5 (K=6) + correction -> +6 tokens (166.5 ms) cpos=136
|
| 222 |
+
[margins] 7.84 5.34 6.76 9.26 2.97 K=6
|
| 223 |
+
verify 30: accepted 5/5 (K=6) + correction -> +6 tokens (162.1 ms) cpos=142
|
| 224 |
+
[margins] 12.89 6.34 10.41 12.46 9.40 K=6
|
| 225 |
+
verify 31: accepted 5/5 (K=6) + correction -> +6 tokens (168.4 ms) cpos=148
|
| 226 |
+
[margins] 5.15 0.24 7.81 2.95 3.29 K=2
|
| 227 |
+
verify 32: accepted 0/1 (K=2) + correction -> +1 tokens (103.5 ms) cpos=149
|
| 228 |
+
[margins] 9.02 10.93 8.21 8.15 4.64 K=6
|
| 229 |
+
verify 33: accepted 5/5 (K=6) + correction -> +6 tokens (160.9 ms) cpos=155
|
| 230 |
+
[margins] 10.01 8.48 8.20 2.98 8.31 K=6
|
| 231 |
+
verify 34: accepted 5/5 (K=6) + correction -> +6 tokens (167.7 ms) cpos=161
|
| 232 |
+
[margins] 10.27 6.65 5.29 9.18 7.17 K=6
|
| 233 |
+
verify 35: accepted 5/5 (K=6) + correction -> +6 tokens (161.7 ms) cpos=167
|
| 234 |
+
[margins] 13.86 5.60 10.62 9.73 10.35 K=6
|
| 235 |
+
verify 36: accepted 5/5 (K=6) + correction -> +6 tokens (168.6 ms) cpos=173
|
| 236 |
+
[margins] 1.49 8.57 9.58 6.94 6.28 K=6
|
| 237 |
+
verify 37: accepted 5/5 (K=6) + correction -> +6 tokens (160.2 ms) cpos=179
|
| 238 |
+
[margins] 8.99 10.53 7.23 8.60 5.99 K=6
|
| 239 |
+
verify 38: accepted 5/5 (K=6) + correction -> +6 tokens (165.7 ms) cpos=185
|
| 240 |
+
[margins] 10.59 10.94 9.91 8.31 9.65 K=6
|
| 241 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (161.8 ms) cpos=191
|
| 242 |
+
[margins] 12.61 9.80 6.13 9.36 0.35 K=5
|
| 243 |
+
verify 40: accepted 4/4 (K=5) + correction -> +5 tokens (152.0 ms) cpos=196
|
| 244 |
+
[margins] 13.52 7.58 10.52 9.55 6.88 K=6
|
| 245 |
+
verify 41: accepted 5/5 (K=6) + correction -> +6 tokens (162.6 ms) cpos=202
|
| 246 |
+
[margins] 14.03 6.04 8.30 6.70 6.92 K=6
|
| 247 |
+
verify 42: accepted 5/5 (K=6) + correction -> +6 tokens (168.7 ms) cpos=208
|
| 248 |
+
[margins] 5.26 0.44 0.37 1.15 0.45 K=2
|
| 249 |
+
verify 43: accepted 0/1 (K=2) + correction -> +1 tokens (103.8 ms) cpos=209
|
| 250 |
+
[margins] 9.77 7.33 7.40 8.25 8.72 K=6
|
| 251 |
+
verify 44: accepted 5/5 (K=6) + correction -> +6 tokens (162.3 ms) cpos=215
|
| 252 |
+
[margins] 8.80 13.01 9.91 8.99 9.31 K=6
|
| 253 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (169.5 ms) cpos=221
|
| 254 |
+
[margins] 11.03 3.52 10.01 9.72 1.10 K=5
|
| 255 |
+
verify 46: accepted 4/4 (K=5) + correction -> +5 tokens (148.6 ms) cpos=226
|
| 256 |
+
[margins] 13.39 6.07 8.14 7.26 6.80 K=6
|
| 257 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (168.4 ms) cpos=232
|
| 258 |
+
[margins] 13.87 6.27 11.28 8.69 9.10 K=6
|
| 259 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (165.9 ms) cpos=238
|
| 260 |
+
|
| 261 |
+
[spec] generated 204 tokens over 48 verifies: mean tokens/verify = 4.25 (block=5, max 6)
|
| 262 |
+
[spec] tokens: 4147 554 1926 270 4105 339 43 1114 1926 270 1178 65 50219 4105 418 270 9517 28 4593 1281 106239 3305 1 1 14 223 19 16 23 14 223 20 16 23 14 223 21 16 23 14
|
| 263 |
+
[spec] SPEC-DECODE: 33.1 ms/tok = 30.20 tok/s (vs base M=1 68.6 ms/tok = 14.59 tok/s -> 2.07x)
|
| 264 |
+
[decode] PREFILL: 41 positions in 692.6 ms = 59.2 tok/s (16.892 ms/tok)
|
| 265 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=2 s=42)...
|
| 266 |
+
[margins] 7.50 0.32 0.94 2.81 0.51 K=2
|
| 267 |
+
verify 1: accepted 1/1 (K=2) + correction -> +2 tokens (99.6 ms) cpos=43
|
| 268 |
+
[margins] 0.63 3.93 2.14 1.16 0.80 K=4
|
| 269 |
+
verify 2: accepted 3/3 (K=4) + correction -> +4 tokens (114.8 ms) cpos=47
|
| 270 |
+
[margins] 0.22 2.54 1.15 0.22 0.26 K=3
|
| 271 |
+
verify 3: accepted 0/2 (K=3) + correction -> +1 tokens (104.4 ms) cpos=48
|
| 272 |
+
[margins] 3.96 5.99 0.35 0.18 0.63 K=3
|
| 273 |
+
verify 4: accepted 0/2 (K=3) + correction -> +1 tokens (109.0 ms) cpos=49
|
| 274 |
+
[margins] 3.00 8.12 1.19 1.44 3.22 K=3
|
| 275 |
+
verify 5: accepted 0/2 (K=3) + correction -> +1 tokens (113.9 ms) cpos=50
|
| 276 |
+
[margins] 1.68 1.40 0.19 0.64 2.19 K=2
|
| 277 |
+
verify 6: accepted 0/1 (K=2) + correction -> +1 tokens (94.5 ms) cpos=51
|
| 278 |
+
[margins] 7.22 4.74 0.62 0.64 0.33 K=3
|
| 279 |
+
verify 7: accepted 1/2 (K=3) + correction -> +2 tokens (110.2 ms) cpos=53
|
| 280 |
+
[margins] 0.40 4.16 6.52 1.19 0.35 K=4
|
| 281 |
+
verify 8: accepted 0/3 (K=4) + correction -> +1 tokens (126.8 ms) cpos=54
|
| 282 |
+
[margins] 0.57 6.93 1.88 1.56 0.12 K=5
|
| 283 |
+
verify 9: accepted 2/4 (K=5) + correction -> +3 tokens (133.1 ms) cpos=57
|
| 284 |
+
[margins] 0.79 4.54 8.52 0.64 0.06 K=4
|
| 285 |
+
verify 10: accepted 0/3 (K=4) + correction -> +1 tokens (126.9 ms) cpos=58
|
| 286 |
+
[margins] 4.49 4.57 2.70 3.76 0.10 K=5
|
| 287 |
+
verify 11: accepted 2/4 (K=5) + correction -> +3 tokens (133.6 ms) cpos=61
|
| 288 |
+
[margins] 2.15 6.35 8.39 4.79 5.58 K=6
|
| 289 |
+
verify 12: accepted 3/5 (K=6) + correction -> +4 tokens (153.2 ms) cpos=65
|
| 290 |
+
[margins] 1.53 4.97 6.37 2.95 6.16 K=6
|
| 291 |
+
verify 13: accepted 3/5 (K=6) + correction -> +4 tokens (152.4 ms) cpos=69
|
| 292 |
+
[margins] 4.49 5.95 5.98 0.08 1.84 K=4
|
| 293 |
+
verify 14: accepted 2/3 (K=4) + correction -> +3 tokens (129.3 ms) cpos=72
|
| 294 |
+
[margins] 3.42 0.06 1.81 3.92 1.14 K=2
|
| 295 |
+
verify 15: accepted 1/1 (K=2) + correction -> +2 tokens (97.6 ms) cpos=74
|
| 296 |
+
[margins] 3.13 5.93 2.12 0.89 4.19 K=4
|
| 297 |
+
verify 16: accepted 1/3 (K=4) + correction -> +2 tokens (126.1 ms) cpos=76
|
| 298 |
+
[margins] 9.25 5.70 4.88 4.23 0.71 K=5
|
| 299 |
+
verify 17: accepted 2/4 (K=5) + correction -> +3 tokens (140.4 ms) cpos=79
|
| 300 |
+
[margins] 17.19 8.77 6.01 5.13 0.36 K=5
|
| 301 |
+
verify 18: accepted 4/4 (K=5) + correction -> +5 tokens (145.6 ms) cpos=84
|
| 302 |
+
[margins] 17.79 10.33 3.38 0.55 1.49 K=4
|
| 303 |
+
verify 19: accepted 2/3 (K=4) + correction -> +3 tokens (130.1 ms) cpos=87
|
| 304 |
+
[margins] 11.62 15.11 13.48 3.45 11.57 K=6
|
| 305 |
+
verify 20: accepted 5/5 (K=6) + correction -> +6 tokens (161.6 ms) cpos=93
|
| 306 |
+
[margins] 8.83 10.90 12.36 7.99 1.87 K=6
|
| 307 |
+
verify 21: accepted 4/5 (K=6) + correction -> +5 tokens (156.9 ms) cpos=98
|
| 308 |
+
[margins] 10.54 8.63 5.43 3.42 2.01 K=6
|
| 309 |
+
verify 22: accepted 4/5 (K=6) + correction -> +5 tokens (164.2 ms) cpos=103
|
| 310 |
+
[margins] 17.76 13.99 10.36 4.17 3.39 K=6
|
| 311 |
+
verify 23: accepted 5/5 (K=6) + correction -> +6 tokens (164.5 ms) cpos=109
|
| 312 |
+
[margins] 9.61 2.43 3.11 6.60 3.91 K=6
|
| 313 |
+
verify 24: accepted 5/5 (K=6) + correction -> +6 tokens (154.6 ms) cpos=115
|
| 314 |
+
[margins] 11.79 9.22 11.77 0.78 0.00 K=4
|
| 315 |
+
verify 25: accepted 3/3 (K=4) + correction -> +4 tokens (130.7 ms) cpos=119
|
| 316 |
+
[margins] 5.08 7.57 0.21 3.23 0.50 K=3
|
| 317 |
+
verify 26: accepted 2/2 (K=3) + correction -> +3 tokens (116.5 ms) cpos=122
|
| 318 |
+
[margins] 15.32 3.70 3.52 9.99 1.52 K=6
|
| 319 |
+
verify 27: accepted 5/5 (K=6) + correction -> +6 tokens (180.0 ms) cpos=128
|
| 320 |
+
[margins] 9.19 11.66 12.86 7.08 4.95 K=6
|
| 321 |
+
verify 28: accepted 5/5 (K=6) + correction -> +6 tokens (161.7 ms) cpos=134
|
| 322 |
+
[margins] 1.91 1.41 10.80 6.17 4.15 K=2
|
| 323 |
+
verify 29: accepted 0/1 (K=2) + correction -> +1 tokens (108.2 ms) cpos=135
|
| 324 |
+
[margins] 14.96 10.05 2.21 2.74 4.62 K=6
|
| 325 |
+
verify 30: accepted 5/5 (K=6) + correction -> +6 tokens (166.3 ms) cpos=141
|
| 326 |
+
[margins] 14.47 12.82 11.24 13.45 4.57 K=6
|
| 327 |
+
verify 31: accepted 5/5 (K=6) + correction -> +6 tokens (158.9 ms) cpos=147
|
| 328 |
+
[margins] 5.95 16.25 10.47 3.69 2.45 K=6
|
| 329 |
+
verify 32: accepted 5/5 (K=6) + correction -> +6 tokens (166.8 ms) cpos=153
|
| 330 |
+
[margins] 1.91 8.67 12.43 7.05 5.84 K=6
|
| 331 |
+
verify 33: accepted 4/5 (K=6) + correction -> +5 tokens (160.9 ms) cpos=158
|
| 332 |
+
[margins] 12.03 6.24 8.87 0.19 0.56 K=4
|
| 333 |
+
verify 34: accepted 3/3 (K=4) + correction -> +4 tokens (129.2 ms) cpos=162
|
| 334 |
+
[margins] 16.46 0.39 1.81 4.16 2.61 K=2
|
| 335 |
+
verify 35: accepted 1/1 (K=2) + correction -> +2 tokens (103.3 ms) cpos=164
|
| 336 |
+
[margins] 12.70 8.44 2.42 0.91 1.04 K=4
|
| 337 |
+
verify 36: accepted 2/3 (K=4) + correction -> +3 tokens (132.2 ms) cpos=167
|
| 338 |
+
[margins] 10.51 14.09 11.70 7.08 2.69 K=6
|
| 339 |
+
verify 37: accepted 4/5 (K=6) + correction -> +5 tokens (165.3 ms) cpos=172
|
| 340 |
+
[margins] 16.98 7.15 11.49 6.23 0.82 K=5
|
| 341 |
+
verify 38: accepted 4/4 (K=5) + correction -> +5 tokens (144.6 ms) cpos=177
|
| 342 |
+
[margins] 15.90 14.98 13.42 9.87 3.89 K=6
|
| 343 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (160.6 ms) cpos=183
|
| 344 |
+
[margins] 15.08 11.26 9.24 1.24 5.92 K=4
|
| 345 |
+
verify 40: accepted 3/3 (K=4) + correction -> +4 tokens (133.0 ms) cpos=187
|
| 346 |
+
[margins] 13.34 11.51 10.98 5.44 0.32 K=5
|
| 347 |
+
verify 41: accepted 4/4 (K=5) + correction -> +5 tokens (152.8 ms) cpos=192
|
| 348 |
+
[margins] 13.53 9.12 7.16 7.33 2.39 K=6
|
| 349 |
+
verify 42: accepted 5/5 (K=6) + correction -> +6 tokens (162.7 ms) cpos=198
|
| 350 |
+
[margins] 14.48 8.19 8.62 0.50 0.72 K=4
|
| 351 |
+
verify 43: accepted 3/3 (K=4) + correction -> +4 tokens (134.3 ms) cpos=202
|
| 352 |
+
[margins] 17.64 12.38 13.30 8.46 1.13 K=5
|
| 353 |
+
verify 44: accepted 4/4 (K=5) + correction -> +5 tokens (146.9 ms) cpos=207
|
| 354 |
+
[margins] 10.77 7.71 7.15 5.29 4.61 K=6
|
| 355 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (161.5 ms) cpos=213
|
| 356 |
+
[margins] 20.90 11.71 5.12 12.46 5.50 K=6
|
| 357 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (159.8 ms) cpos=219
|
| 358 |
+
[margins] 20.42 10.61 19.62 5.72 14.36 K=6
|
| 359 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (170.1 ms) cpos=225
|
| 360 |
+
[margins] 8.01 24.34 7.75 14.77 9.32 K=6
|
| 361 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (163.2 ms) cpos=231
|
| 362 |
+
[margins] 27.61 10.29 15.97 4.38 7.61 K=6
|
| 363 |
+
verify 49: accepted 5/5 (K=6) + correction -> +6 tokens (170.1 ms) cpos=237
|
| 364 |
+
[margins] 11.95 13.21 6.85 0.98 7.47 K=4
|
| 365 |
+
verify 50: accepted 3/3 (K=4) + correction -> +4 tokens (134.7 ms) cpos=241
|
| 366 |
+
|
| 367 |
+
[spec] generated 200 tokens over 50 verifies: mean tokens/verify = 4.00 (block=5, max 6)
|
| 368 |
+
[spec] tokens: 1 1 1 1 1 1 50 1697 1 16 1 50 1697 16 1 50 1697 16 1 50 1697 16 1 50 1697 16 1 50 1697 16 20692 50 1697 16 791 50 1697 4394 1015 50
|
| 369 |
+
[spec] SPEC-DECODE: 34.9 ms/tok = 28.62 tok/s (vs base M=1 68.6 ms/tok = 14.59 tok/s -> 1.96x)
|
| 370 |
+
[decode] PREFILL: 26 positions in 454.0 ms = 57.3 tok/s (17.460 ms/tok)
|
| 371 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=3 s=27)...
|
| 372 |
+
[margins] 1.81 2.01 0.97 0.54 0.62 K=3
|
| 373 |
+
verify 1: accepted 1/2 (K=3) + correction -> +2 tokens (114.6 ms) cpos=28
|
| 374 |
+
[margins] 4.69 2.59 0.65 1.53 0.57 K=3
|
| 375 |
+
verify 2: accepted 1/2 (K=3) + correction -> +2 tokens (110.0 ms) cpos=30
|
| 376 |
+
[margins] 2.84 0.76 1.05 0.11 0.16 K=2
|
| 377 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (102.9 ms) cpos=32
|
| 378 |
+
[margins] 3.02 2.88 2.09 0.38 0.68 K=4
|
| 379 |
+
verify 4: accepted 3/3 (K=4) + correction -> +4 tokens (118.0 ms) cpos=36
|
| 380 |
+
[margins] 2.69 6.57 1.99 1.51 1.50 K=6
|
| 381 |
+
verify 5: accepted 5/5 (K=6) + correction -> +6 tokens (143.0 ms) cpos=42
|
| 382 |
+
[margins] 1.87 9.82 1.85 4.64 1.52 K=6
|
| 383 |
+
verify 6: accepted 5/5 (K=6) + correction -> +6 tokens (149.5 ms) cpos=48
|
| 384 |
+
[margins] 0.19 12.95 2.80 7.99 3.05 K=6
|
| 385 |
+
verify 7: accepted 0/5 (K=6) + correction -> +1 tokens (148.3 ms) cpos=49
|
| 386 |
+
[margins] 8.19 2.23 8.80 2.00 6.75 K=6
|
| 387 |
+
verify 8: accepted 5/5 (K=6) + correction -> +6 tokens (144.1 ms) cpos=55
|
| 388 |
+
[margins] 7.28 0.46 8.02 3.21 6.54 K=2
|
| 389 |
+
verify 9: accepted 1/1 (K=2) + correction -> +2 tokens (102.5 ms) cpos=57
|
| 390 |
+
[margins] 8.02 1.59 9.09 2.61 6.00 K=6
|
| 391 |
+
verify 10: accepted 5/5 (K=6) + correction -> +6 tokens (145.3 ms) cpos=63
|
| 392 |
+
[margins] 6.93 0.98 7.96 3.27 6.06 K=2
|
| 393 |
+
verify 11: accepted 1/1 (K=2) + correction -> +2 tokens (103.4 ms) cpos=65
|
| 394 |
+
[margins] 6.73 2.32 8.54 2.97 6.16 K=6
|
| 395 |
+
verify 12: accepted 5/5 (K=6) + correction -> +6 tokens (144.7 ms) cpos=71
|
| 396 |
+
[margins] 8.04 0.74 9.61 2.75 6.56 K=2
|
| 397 |
+
verify 13: accepted 1/1 (K=2) + correction -> +2 tokens (103.5 ms) cpos=73
|
| 398 |
+
[margins] 7.70 0.62 9.84 3.24 6.83 K=2
|
| 399 |
+
verify 14: accepted 1/1 (K=2) + correction -> +2 tokens (99.6 ms) cpos=75
|
| 400 |
+
[margins] 8.65 2.08 7.54 2.09 4.32 K=6
|
| 401 |
+
verify 15: accepted 0/5 (K=6) + correction -> +1 tokens (155.6 ms) cpos=76
|
| 402 |
+
[margins] 2.09 6.23 0.29 1.14 0.15 K=3
|
| 403 |
+
verify 16: accepted 0/2 (K=3) + correction -> +1 tokens (110.5 ms) cpos=77
|
| 404 |
+
[margins] 0.19 1.45 1.88 1.37 1.83 K=2
|
| 405 |
+
verify 17: accepted 0/1 (K=2) + correction -> +1 tokens (97.8 ms) cpos=78
|
| 406 |
+
[margins] 1.90 2.92 1.11 2.68 1.86 K=3
|
| 407 |
+
verify 18: accepted 2/2 (K=3) + correction -> +3 tokens (113.2 ms) cpos=81
|
| 408 |
+
[margins] 2.16 0.11 1.20 0.32 0.64 K=2
|
| 409 |
+
verify 19: accepted 1/1 (K=2) + correction -> +2 tokens (96.8 ms) cpos=83
|
| 410 |
+
[margins] 1.07 0.27 0.61 0.21 0.54 K=2
|
| 411 |
+
verify 20: accepted 1/1 (K=2) + correction -> +2 tokens (101.4 ms) cpos=85
|
| 412 |
+
[margins] 4.84 1.92 0.46 0.66 1.37 K=3
|
| 413 |
+
verify 21: accepted 1/2 (K=3) + correction -> +2 tokens (112.4 ms) cpos=87
|
| 414 |
+
[margins] 3.66 3.10 1.47 2.70 0.72 K=3
|
| 415 |
+
verify 22: accepted 1/2 (K=3) + correction -> +2 tokens (115.0 ms) cpos=89
|
| 416 |
+
[margins] 1.41 1.18 0.76 1.49 0.34 K=2
|
| 417 |
+
verify 23: accepted 1/1 (K=2) + correction -> +2 tokens (98.6 ms) cpos=91
|
| 418 |
+
[margins] 4.98 0.33 1.75 2.50 0.12 K=2
|
| 419 |
+
verify 24: accepted 1/1 (K=2) + correction -> +2 tokens (101.4 ms) cpos=93
|
| 420 |
+
[margins] 3.48 0.12 4.38 3.31 0.31 K=2
|
| 421 |
+
verify 25: accepted 1/1 (K=2) + correction -> +2 tokens (96.8 ms) cpos=95
|
| 422 |
+
[margins] 7.46 1.18 3.63 2.02 0.06 K=2
|
| 423 |
+
verify 26: accepted 1/1 (K=2) + correction -> +2 tokens (102.1 ms) cpos=97
|
| 424 |
+
[margins] 2.36 2.19 0.27 3.31 0.14 K=3
|
| 425 |
+
verify 27: accepted 2/2 (K=3) + correction -> +3 tokens (117.7 ms) cpos=100
|
| 426 |
+
[margins] 0.19 0.09 2.48 1.59 0.91 K=2
|
| 427 |
+
verify 28: accepted 0/1 (K=2) + correction -> +1 tokens (98.2 ms) cpos=101
|
| 428 |
+
[margins] 3.61 0.93 0.19 3.50 2.16 K=2
|
| 429 |
+
verify 29: accepted 1/1 (K=2) + correction -> +2 tokens (100.5 ms) cpos=103
|
| 430 |
+
[margins] 5.84 7.10 1.14 4.16 6.96 K=3
|
| 431 |
+
verify 30: accepted 2/2 (K=3) + correction -> +3 tokens (112.5 ms) cpos=106
|
| 432 |
+
[margins] 7.16 5.43 0.47 5.96 1.75 K=3
|
| 433 |
+
verify 31: accepted 2/2 (K=3) + correction -> +3 tokens (112.8 ms) cpos=109
|
| 434 |
+
[margins] 10.09 1.44 2.74 1.42 1.25 K=2
|
| 435 |
+
verify 32: accepted 1/1 (K=2) + correction -> +2 tokens (97.8 ms) cpos=111
|
| 436 |
+
[margins] 2.17 6.56 0.43 0.33 1.52 K=3
|
| 437 |
+
verify 33: accepted 2/2 (K=3) + correction -> +3 tokens (116.4 ms) cpos=114
|
| 438 |
+
[margins] 0.81 10.17 2.07 1.53 2.11 K=6
|
| 439 |
+
verify 34: accepted 2/5 (K=6) + correction -> +3 tokens (161.1 ms) cpos=117
|
| 440 |
+
[margins] 1.10 5.43 4.06 3.21 9.54 K=6
|
| 441 |
+
verify 35: accepted 5/5 (K=6) + correction -> +6 tokens (161.5 ms) cpos=123
|
| 442 |
+
[margins] 9.90 11.81 4.67 12.77 4.09 K=6
|
| 443 |
+
verify 36: accepted 5/5 (K=6) + correction -> +6 tokens (177.3 ms) cpos=129
|
| 444 |
+
[margins] 11.37 12.48 11.74 8.61 3.31 K=6
|
| 445 |
+
verify 37: accepted 5/5 (K=6) + correction -> +6 tokens (160.2 ms) cpos=135
|
| 446 |
+
[margins] 3.77 1.85 0.99 0.76 3.05 K=3
|
| 447 |
+
verify 38: accepted 1/2 (K=3) + correction -> +2 tokens (114.5 ms) cpos=137
|
| 448 |
+
[margins] 2.78 0.20 1.82 1.09 2.98 K=2
|
| 449 |
+
verify 39: accepted 0/1 (K=2) + correction -> +1 tokens (101.3 ms) cpos=138
|
| 450 |
+
[margins] 0.39 1.48 1.11 1.96 0.24 K=2
|
| 451 |
+
verify 40: accepted 1/1 (K=2) + correction -> +2 tokens (103.2 ms) cpos=140
|
| 452 |
+
[margins] 3.68 1.54 0.49 0.49 0.51 K=3
|
| 453 |
+
verify 41: accepted 0/2 (K=3) + correction -> +1 tokens (112.2 ms) cpos=141
|
| 454 |
+
[margins] 1.83 0.43 1.11 0.56 0.77 K=2
|
| 455 |
+
verify 42: accepted 1/1 (K=2) + correction -> +2 tokens (99.2 ms) cpos=143
|
| 456 |
+
[margins] 0.41 0.21 0.84 0.13 0.87 K=2
|
| 457 |
+
verify 43: accepted 0/1 (K=2) + correction -> +1 tokens (105.1 ms) cpos=144
|
| 458 |
+
[margins] 1.31 2.40 1.46 2.92 0.41 K=3
|
| 459 |
+
verify 44: accepted 1/2 (K=3) + correction -> +2 tokens (115.7 ms) cpos=146
|
| 460 |
+
[margins] 7.00 2.07 1.94 1.72 0.24 K=5
|
| 461 |
+
verify 45: accepted 2/4 (K=5) + correction -> +3 tokens (140.1 ms) cpos=149
|
| 462 |
+
[margins] 0.91 2.29 3.09 0.83 1.36 K=4
|
| 463 |
+
verify 46: accepted 0/3 (K=4) + correction -> +1 tokens (128.8 ms) cpos=150
|
| 464 |
+
[margins] 1.21 0.91 0.16 2.17 0.00 K=2
|
| 465 |
+
verify 47: accepted 1/1 (K=2) + correction -> +2 tokens (101.8 ms) cpos=152
|
| 466 |
+
[margins] 4.04 0.59 0.89 1.42 1.17 K=2
|
| 467 |
+
verify 48: accepted 1/1 (K=2) + correction -> +2 tokens (99.1 ms) cpos=154
|
| 468 |
+
[margins] 0.96 0.92 3.13 0.48 0.28 K=2
|
| 469 |
+
verify 49: accepted 1/1 (K=2) + correction -> +2 tokens (105.0 ms) cpos=156
|
| 470 |
+
[margins] 4.76 2.16 0.83 0.27 0.41 K=3
|
| 471 |
+
verify 50: accepted 1/2 (K=3) + correction -> +2 tokens (110.4 ms) cpos=158
|
| 472 |
+
[margins] 3.40 1.79 1.87 0.70 0.85 K=4
|
| 473 |
+
verify 51: accepted 3/3 (K=4) + correction -> +4 tokens (131.1 ms) cpos=162
|
| 474 |
+
[margins] 5.42 3.08 0.38 0.19 0.87 K=3
|
| 475 |
+
verify 52: accepted 2/2 (K=3) + correction -> +3 tokens (114.6 ms) cpos=165
|
| 476 |
+
[margins] 3.36 1.57 1.95 0.98 2.39 K=4
|
| 477 |
+
verify 53: accepted 2/3 (K=4) + correction -> +3 tokens (128.8 ms) cpos=168
|
| 478 |
+
[margins] 4.59 1.87 6.81 2.60 0.30 K=5
|
| 479 |
+
verify 54: accepted 4/4 (K=5) + correction -> +5 tokens (143.9 ms) cpos=173
|
| 480 |
+
[margins] 0.05 1.14 3.35 0.06 0.20 K=2
|
| 481 |
+
verify 55: accepted 0/1 (K=2) + correction -> +1 tokens (100.9 ms) cpos=174
|
| 482 |
+
[margins] 0.06 0.46 1.69 3.08 0.87 K=2
|
| 483 |
+
verify 56: accepted 0/1 (K=2) + correction -> +1 tokens (104.3 ms) cpos=175
|
| 484 |
+
[margins] 0.24 1.83 1.19 0.52 1.96 K=3
|
| 485 |
+
verify 57: accepted 1/2 (K=3) + correction -> +2 tokens (118.6 ms) cpos=177
|
| 486 |
+
[margins] 5.29 1.47 2.24 1.71 2.80 K=2
|
| 487 |
+
verify 58: accepted 1/1 (K=2) + correction -> +2 tokens (101.0 ms) cpos=179
|
| 488 |
+
[margins] 3.37 3.22 3.07 1.45 0.89 K=4
|
| 489 |
+
verify 59: accepted 1/3 (K=4) + correction -> +2 tokens (130.8 ms) cpos=181
|
| 490 |
+
[margins] 5.26 0.82 0.40 1.47 1.37 K=2
|
| 491 |
+
verify 60: accepted 1/1 (K=2) + correction -> +2 tokens (99.7 ms) cpos=183
|
| 492 |
+
[margins] 2.70 3.66 5.48 2.95 3.14 K=6
|
| 493 |
+
verify 61: accepted 2/5 (K=6) + correction -> +3 tokens (160.2 ms) cpos=186
|
| 494 |
+
[margins] 3.20 3.05 0.34 0.49 0.64 K=3
|
| 495 |
+
verify 62: accepted 2/2 (K=3) + correction -> +3 tokens (117.9 ms) cpos=189
|
| 496 |
+
[margins] 3.54 1.52 0.43 0.18 0.80 K=3
|
| 497 |
+
verify 63: accepted 2/2 (K=3) + correction -> +3 tokens (119.4 ms) cpos=192
|
| 498 |
+
[margins] 6.39 0.67 0.28 0.97 0.18 K=2
|
| 499 |
+
verify 64: accepted 1/1 (K=2) + correction -> +2 tokens (100.2 ms) cpos=194
|
| 500 |
+
[margins] 0.83 1.55 3.25 1.28 0.17 K=4
|
| 501 |
+
verify 65: accepted 0/3 (K=4) + correction -> +1 tokens (131.2 ms) cpos=195
|
| 502 |
+
[margins] 1.85 1.14 1.72 3.84 0.87 K=2
|
| 503 |
+
verify 66: accepted 1/1 (K=2) + correction -> +2 tokens (103.5 ms) cpos=197
|
| 504 |
+
[margins] 1.15 0.92 6.52 1.54 2.74 K=2
|
| 505 |
+
verify 67: accepted 0/1 (K=2) + correction -> +1 tokens (99.9 ms) cpos=198
|
| 506 |
+
[margins] 1.92 1.17 1.27 4.42 1.07 K=2
|
| 507 |
+
verify 68: accepted 0/1 (K=2) + correction -> +1 tokens (105.6 ms) cpos=199
|
| 508 |
+
[margins] 4.06 7.58 7.47 1.67 5.25 K=6
|
| 509 |
+
verify 69: accepted 0/5 (K=6) + correction -> +1 tokens (165.7 ms) cpos=200
|
| 510 |
+
[margins] 7.45 3.49 0.82 3.05 2.49 K=3
|
| 511 |
+
verify 70: accepted 2/2 (K=3) + correction -> +3 tokens (112.5 ms) cpos=203
|
| 512 |
+
[margins] 4.33 3.72 3.21 2.49 1.29 K=5
|
| 513 |
+
verify 71: accepted 1/4 (K=5) + correction -> +2 tokens (143.6 ms) cpos=205
|
| 514 |
+
[margins] 2.44 0.73 0.11 0.42 1.18 K=2
|
| 515 |
+
verify 72: accepted 1/1 (K=2) + correction -> +2 tokens (99.6 ms) cpos=207
|
| 516 |
+
[margins] 0.13 1.15 2.02 3.37 4.36 K=2
|
| 517 |
+
verify 73: accepted 0/1 (K=2) + correction -> +1 tokens (103.8 ms) cpos=208
|
| 518 |
+
[margins] 11.24 1.00 1.72 4.77 1.02 K=2
|
| 519 |
+
verify 74: accepted 1/1 (K=2) + correction -> +2 tokens (101.3 ms) cpos=210
|
| 520 |
+
[margins] 3.14 6.22 1.72 1.90 5.02 K=6
|
| 521 |
+
verify 75: accepted 2/5 (K=6) + correction -> +3 tokens (159.6 ms) cpos=213
|
| 522 |
+
[margins] 1.00 0.01 0.29 1.02 0.39 K=2
|
| 523 |
+
verify 76: accepted 1/1 (K=2) + correction -> +2 tokens (99.9 ms) cpos=215
|
| 524 |
+
[margins] 3.74 2.06 4.65 5.00 2.81 K=6
|
| 525 |
+
verify 77: accepted 4/5 (K=6) + correction -> +5 tokens (166.4 ms) cpos=220
|
| 526 |
+
[margins] 4.02 1.59 2.76 0.36 1.83 K=4
|
| 527 |
+
verify 78: accepted 0/3 (K=4) + correction -> +1 tokens (133.1 ms) cpos=221
|
| 528 |
+
[margins] 11.63 2.60 2.77 0.07 4.97 K=4
|
| 529 |
+
verify 79: accepted 3/3 (K=4) + correction -> +4 tokens (131.7 ms) cpos=225
|
| 530 |
+
[margins] 11.06 7.13 0.94 0.99 0.24 K=3
|
| 531 |
+
verify 80: accepted 2/2 (K=3) + correction -> +3 tokens (120.2 ms) cpos=228
|
| 532 |
+
|
| 533 |
+
[spec] generated 202 tokens over 80 verifies: mean tokens/verify = 2.52 (block=5, max 6)
|
| 534 |
+
[spec] tokens: 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16
|
| 535 |
+
[spec] SPEC-DECODE: 47.1 ms/tok = 21.24 tok/s (vs base M=1 68.6 ms/tok = 14.59 tok/s -> 1.46x)
|
| 536 |
+
[decode] PREFILL: 14 positions in 284.8 ms = 49.2 tok/s (20.341 ms/tok)
|
| 537 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=4 s=15)...
|
| 538 |
+
[margins] 0.16 0.38 1.56 1.71 0.08 K=2
|
| 539 |
+
verify 1: accepted 0/1 (K=2) + correction -> +1 tokens (102.1 ms) cpos=15
|
| 540 |
+
[margins] 0.46 1.61 0.33 0.85 0.22 K=3
|
| 541 |
+
verify 2: accepted 1/2 (K=3) + correction -> +2 tokens (111.7 ms) cpos=17
|
| 542 |
+
[margins] 0.37 0.53 0.59 0.92 0.69 K=2
|
| 543 |
+
verify 3: accepted 0/1 (K=2) + correction -> +1 tokens (95.4 ms) cpos=18
|
| 544 |
+
[margins] 1.32 0.81 0.33 0.40 1.13 K=2
|
| 545 |
+
verify 4: accepted 1/1 (K=2) + correction -> +2 tokens (99.4 ms) cpos=20
|
| 546 |
+
[margins] 0.84 1.20 0.59 0.51 1.36 K=2
|
| 547 |
+
verify 5: accepted 1/1 (K=2) + correction -> +2 tokens (94.4 ms) cpos=22
|
| 548 |
+
[margins] 1.78 1.01 0.65 0.37 0.42 K=2
|
| 549 |
+
verify 6: accepted 1/1 (K=2) + correction -> +2 tokens (100.8 ms) cpos=24
|
| 550 |
+
[margins] 0.17 0.60 0.21 0.70 3.89 K=2
|
| 551 |
+
verify 7: accepted 1/1 (K=2) + correction -> +2 tokens (96.6 ms) cpos=26
|
| 552 |
+
[margins] 0.53 0.13 0.62 0.51 0.57 K=2
|
| 553 |
+
verify 8: accepted 0/1 (K=2) + correction -> +1 tokens (100.7 ms) cpos=27
|
| 554 |
+
[margins] 0.21 0.42 0.30 1.04 0.31 K=2
|
| 555 |
+
verify 9: accepted 1/1 (K=2) + correction -> +2 tokens (103.5 ms) cpos=29
|
| 556 |
+
[margins] 2.61 2.68 0.59 3.31 0.58 K=3
|
| 557 |
+
verify 10: accepted 2/2 (K=3) + correction -> +3 tokens (112.8 ms) cpos=32
|
| 558 |
+
[margins] 1.03 1.84 0.10 0.09 2.52 K=3
|
| 559 |
+
verify 11: accepted 1/2 (K=3) + correction -> +2 tokens (107.3 ms) cpos=34
|
| 560 |
+
[margins] 0.50 0.15 0.05 1.12 0.28 K=2
|
| 561 |
+
verify 12: accepted 1/1 (K=2) + correction -> +2 tokens (99.1 ms) cpos=36
|
| 562 |
+
[margins] 0.65 1.84 12.52 1.18 2.14 K=4
|
| 563 |
+
verify 13: accepted 0/3 (K=4) + correction -> +1 tokens (122.9 ms) cpos=37
|
| 564 |
+
[margins] 0.63 2.84 0.19 0.67 0.20 K=3
|
| 565 |
+
verify 14: accepted 1/2 (K=3) + correction -> +2 tokens (112.8 ms) cpos=39
|
| 566 |
+
[margins] 2.88 0.96 0.07 0.16 0.10 K=2
|
| 567 |
+
verify 15: accepted 0/1 (K=2) + correction -> +1 tokens (99.4 ms) cpos=40
|
| 568 |
+
[margins] 3.05 3.41 3.29 1.35 0.82 K=4
|
| 569 |
+
verify 16: accepted 1/3 (K=4) + correction -> +2 tokens (127.1 ms) cpos=42
|
| 570 |
+
[margins] 0.58 0.40 1.48 0.44 0.74 K=2
|
| 571 |
+
verify 17: accepted 1/1 (K=2) + correction -> +2 tokens (101.4 ms) cpos=44
|
| 572 |
+
[margins] 1.88 8.17 0.74 1.11 2.30 K=3
|
| 573 |
+
verify 18: accepted 2/2 (K=3) + correction -> +3 tokens (109.5 ms) cpos=47
|
| 574 |
+
[margins] 3.57 7.41 2.36 1.21 2.88 K=4
|
| 575 |
+
verify 19: accepted 3/3 (K=4) + correction -> +4 tokens (125.7 ms) cpos=51
|
| 576 |
+
[margins] 2.84 0.23 0.04 1.91 0.13 K=2
|
| 577 |
+
verify 20: accepted 0/1 (K=2) + correction -> +1 tokens (101.0 ms) cpos=52
|
| 578 |
+
[margins] 2.00 1.79 1.28 0.68 3.93 K=3
|
| 579 |
+
verify 21: accepted 0/2 (K=3) + correction -> +1 tokens (108.4 ms) cpos=53
|
| 580 |
+
[margins] 7.63 3.19 2.09 0.74 2.61 K=4
|
| 581 |
+
verify 22: accepted 2/3 (K=4) + correction -> +3 tokens (129.2 ms) cpos=56
|
| 582 |
+
[margins] 4.48 1.80 3.86 3.96 0.90 K=5
|
| 583 |
+
verify 23: accepted 4/4 (K=5) + correction -> +5 tokens (136.4 ms) cpos=61
|
| 584 |
+
[margins] 1.77 1.43 0.18 1.26 0.11 K=2
|
| 585 |
+
verify 24: accepted 0/1 (K=2) + correction -> +1 tokens (98.1 ms) cpos=62
|
| 586 |
+
[margins] 1.27 0.51 1.71 2.00 2.49 K=2
|
| 587 |
+
verify 25: accepted 0/1 (K=2) + correction -> +1 tokens (100.1 ms) cpos=63
|
| 588 |
+
[margins] 1.05 1.54 0.98 1.31 0.02 K=3
|
| 589 |
+
verify 26: accepted 2/2 (K=3) + correction -> +3 tokens (114.4 ms) cpos=66
|
| 590 |
+
[margins] 0.98 3.76 0.73 0.20 0.32 K=3
|
| 591 |
+
verify 27: accepted 0/2 (K=3) + correction -> +1 tokens (112.9 ms) cpos=67
|
| 592 |
+
[margins] 1.68 0.41 0.79 2.20 0.99 K=2
|
| 593 |
+
verify 28: accepted 1/1 (K=2) + correction -> +2 tokens (102.9 ms) cpos=69
|
| 594 |
+
[margins] 0.05 0.91 1.19 0.32 0.19 K=2
|
| 595 |
+
verify 29: accepted 0/1 (K=2) + correction -> +1 tokens (99.2 ms) cpos=70
|
| 596 |
+
[margins] 1.85 0.79 0.66 0.32 0.70 K=2
|
| 597 |
+
verify 30: accepted 0/1 (K=2) + correction -> +1 tokens (102.1 ms) cpos=71
|
| 598 |
+
[margins] 0.27 1.16 2.62 0.25 0.21 K=2
|
| 599 |
+
verify 31: accepted 0/1 (K=2) + correction -> +1 tokens (103.1 ms) cpos=72
|
| 600 |
+
[margins] 1.59 0.07 2.23 0.65 0.25 K=2
|
| 601 |
+
verify 32: accepted 0/1 (K=2) + correction -> +1 tokens (97.7 ms) cpos=73
|
| 602 |
+
[margins] 6.14 1.82 0.57 0.49 0.85 K=3
|
| 603 |
+
verify 33: accepted 2/2 (K=3) + correction -> +3 tokens (113.2 ms) cpos=76
|
| 604 |
+
[margins] 2.01 4.25 1.67 1.33 1.41 K=4
|
| 605 |
+
verify 34: accepted 0/3 (K=4) + correction -> +1 tokens (127.5 ms) cpos=77
|
| 606 |
+
[margins] 4.76 1.75 1.65 2.62 0.84 K=5
|
| 607 |
+
verify 35: accepted 2/4 (K=5) + correction -> +3 tokens (139.8 ms) cpos=80
|
| 608 |
+
[margins] 1.74 5.40 1.91 2.61 8.86 K=6
|
| 609 |
+
verify 36: accepted 5/5 (K=6) + correction -> +6 tokens (162.7 ms) cpos=86
|
| 610 |
+
[margins] 4.97 5.21 4.16 3.07 0.20 K=5
|
| 611 |
+
verify 37: accepted 2/4 (K=5) + correction -> +3 tokens (129.5 ms) cpos=89
|
| 612 |
+
[margins] 8.80 3.99 2.99 1.08 0.46 K=4
|
| 613 |
+
verify 38: accepted 1/3 (K=4) + correction -> +2 tokens (122.7 ms) cpos=91
|
| 614 |
+
[margins] 5.98 3.97 0.31 1.52 3.71 K=3
|
| 615 |
+
verify 39: accepted 1/2 (K=3) + correction -> +2 tokens (111.3 ms) cpos=93
|
| 616 |
+
[margins] 3.78 0.59 5.38 4.01 0.42 K=2
|
| 617 |
+
verify 40: accepted 1/1 (K=2) + correction -> +2 tokens (100.5 ms) cpos=95
|
| 618 |
+
[margins] 4.26 1.06 2.54 2.08 4.23 K=2
|
| 619 |
+
verify 41: accepted 1/1 (K=2) + correction -> +2 tokens (105.6 ms) cpos=97
|
| 620 |
+
[margins] 2.80 5.80 2.25 0.88 2.75 K=4
|
| 621 |
+
verify 42: accepted 3/3 (K=4) + correction -> +4 tokens (122.7 ms) cpos=101
|
| 622 |
+
[margins] 2.43 8.37 2.70 4.64 3.36 K=6
|
| 623 |
+
verify 43: accepted 5/5 (K=6) + correction -> +6 tokens (147.2 ms) cpos=107
|
| 624 |
+
[margins] 2.13 8.97 2.57 5.45 3.53 K=6
|
| 625 |
+
verify 44: accepted 5/5 (K=6) + correction -> +6 tokens (153.8 ms) cpos=113
|
| 626 |
+
[margins] 1.40 7.89 2.50 4.33 3.13 K=6
|
| 627 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (148.2 ms) cpos=119
|
| 628 |
+
[margins] 3.02 7.91 3.43 4.42 2.92 K=6
|
| 629 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (156.2 ms) cpos=125
|
| 630 |
+
[margins] 3.49 9.27 3.86 5.00 3.51 K=6
|
| 631 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (163.1 ms) cpos=131
|
| 632 |
+
[margins] 2.52 7.72 3.63 4.55 3.58 K=6
|
| 633 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (155.8 ms) cpos=137
|
| 634 |
+
[margins] 3.35 9.43 3.33 3.90 3.50 K=6
|
| 635 |
+
verify 49: accepted 5/5 (K=6) + correction -> +6 tokens (149.7 ms) cpos=143
|
| 636 |
+
[margins] 4.02 9.34 3.34 4.46 2.77 K=6
|
| 637 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (156.7 ms) cpos=149
|
| 638 |
+
[margins] 2.48 10.25 2.61 5.45 3.30 K=6
|
| 639 |
+
verify 51: accepted 5/5 (K=6) + correction -> +6 tokens (151.5 ms) cpos=155
|
| 640 |
+
[margins] 3.50 10.01 2.75 4.97 3.05 K=6
|
| 641 |
+
verify 52: accepted 0/5 (K=6) + correction -> +1 tokens (157.0 ms) cpos=156
|
| 642 |
+
[margins] 5.71 2.68 6.91 2.15 1.43 K=5
|
| 643 |
+
verify 53: accepted 1/4 (K=5) + correction -> +2 tokens (138.7 ms) cpos=158
|
| 644 |
+
[margins] 5.00 1.16 1.39 0.25 7.19 K=2
|
| 645 |
+
verify 54: accepted 0/1 (K=2) + correction -> +1 tokens (104.3 ms) cpos=159
|
| 646 |
+
[margins] 7.64 1.30 0.25 0.64 0.35 K=2
|
| 647 |
+
verify 55: accepted 1/1 (K=2) + correction -> +2 tokens (104.5 ms) cpos=161
|
| 648 |
+
[margins] 8.47 5.58 1.63 3.76 1.63 K=6
|
| 649 |
+
verify 56: accepted 4/5 (K=6) + correction -> +5 tokens (157.1 ms) cpos=166
|
| 650 |
+
[margins] 1.01 0.25 5.45 0.39 1.11 K=2
|
| 651 |
+
verify 57: accepted 0/1 (K=2) + correction -> +1 tokens (108.1 ms) cpos=167
|
| 652 |
+
[margins] 10.05 3.56 7.92 8.11 4.05 K=6
|
| 653 |
+
verify 58: accepted 5/5 (K=6) + correction -> +6 tokens (165.8 ms) cpos=173
|
| 654 |
+
[margins] 5.40 1.66 1.48 3.13 0.77 K=3
|
| 655 |
+
verify 59: accepted 1/2 (K=3) + correction -> +2 tokens (118.5 ms) cpos=175
|
| 656 |
+
[margins] 7.48 8.47 0.91 0.56 4.98 K=3
|
| 657 |
+
verify 60: accepted 2/2 (K=3) + correction -> +3 tokens (118.5 ms) cpos=178
|
| 658 |
+
[margins] 16.85 13.37 11.71 10.05 8.02 K=6
|
| 659 |
+
verify 61: accepted 5/5 (K=6) + correction -> +6 tokens (167.2 ms) cpos=184
|
| 660 |
+
[margins] 5.08 7.59 10.11 12.57 5.04 K=6
|
| 661 |
+
verify 62: accepted 5/5 (K=6) + correction -> +6 tokens (162.2 ms) cpos=190
|
| 662 |
+
[margins] 9.89 5.14 8.92 7.33 10.45 K=6
|
| 663 |
+
verify 63: accepted 5/5 (K=6) + correction -> +6 tokens (169.4 ms) cpos=196
|
| 664 |
+
[margins] 13.08 9.14 8.38 9.30 2.09 K=6
|
| 665 |
+
verify 64: accepted 4/5 (K=6) + correction -> +5 tokens (165.1 ms) cpos=201
|
| 666 |
+
[margins] 3.62 10.15 10.85 15.04 7.39 K=6
|
| 667 |
+
verify 65: accepted 5/5 (K=6) + correction -> +6 tokens (163.0 ms) cpos=207
|
| 668 |
+
[margins] 10.30 6.17 8.72 10.41 11.32 K=6
|
| 669 |
+
verify 66: accepted 5/5 (K=6) + correction -> +6 tokens (167.5 ms) cpos=213
|
| 670 |
+
[margins] 12.93 14.42 12.35 9.42 4.25 K=6
|
| 671 |
+
verify 67: accepted 4/5 (K=6) + correction -> +5 tokens (163.5 ms) cpos=218
|
| 672 |
+
|
| 673 |
+
[spec] generated 204 tokens over 67 verifies: mean tokens/verify = 3.04 (block=5, max 6)
|
| 674 |
+
[spec] tokens: 5715 14 295 834 10175 14 8470 3939 436 344 2239 362 4197 339 35 126664 23809 16765 270 3077 305 1990 23714 538 9479 21121 35977 2184 47270 34788 14 832 851 588 366 99782 1082 20351 14319 35977
|
| 675 |
+
[spec] SPEC-DECODE: 40.8 ms/tok = 24.53 tok/s (vs base M=1 68.6 ms/tok = 14.59 tok/s -> 1.68x)
|
| 676 |
+
[decode] PREFILL: 82 positions in 1289.8 ms = 63.6 tok/s (15.729 ms/tok)
|
| 677 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=5 s=83)...
|
| 678 |
+
[margins] 6.43 3.13 1.20 0.45 3.60 K=3
|
| 679 |
+
verify 1: accepted 1/2 (K=3) + correction -> +2 tokens (117.9 ms) cpos=84
|
| 680 |
+
[margins] 0.08 0.12 0.52 0.85 1.56 K=2
|
| 681 |
+
verify 2: accepted 0/1 (K=2) + correction -> +1 tokens (98.5 ms) cpos=85
|
| 682 |
+
[margins] 0.18 0.56 0.30 0.75 1.01 K=2
|
| 683 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (98.9 ms) cpos=87
|
| 684 |
+
[margins] 5.70 2.01 4.26 0.55 0.64 K=4
|
| 685 |
+
verify 4: accepted 3/3 (K=4) + correction -> +4 tokens (129.0 ms) cpos=91
|
| 686 |
+
[margins] 12.37 6.46 6.89 4.06 3.38 K=6
|
| 687 |
+
verify 5: accepted 5/5 (K=6) + correction -> +6 tokens (163.3 ms) cpos=97
|
| 688 |
+
[margins] 8.79 3.44 2.08 0.63 1.47 K=4
|
| 689 |
+
verify 6: accepted 3/3 (K=4) + correction -> +4 tokens (128.7 ms) cpos=101
|
| 690 |
+
[margins] 5.17 0.42 0.22 0.39 0.06 K=2
|
| 691 |
+
verify 7: accepted 1/1 (K=2) + correction -> +2 tokens (102.0 ms) cpos=103
|
| 692 |
+
[margins] 2.64 0.88 1.77 0.63 1.76 K=2
|
| 693 |
+
verify 8: accepted 1/1 (K=2) + correction -> +2 tokens (104.3 ms) cpos=105
|
| 694 |
+
[margins] 8.81 7.34 6.17 5.27 0.83 K=5
|
| 695 |
+
verify 9: accepted 4/4 (K=5) + correction -> +5 tokens (141.2 ms) cpos=110
|
| 696 |
+
[margins] 13.15 7.81 8.61 4.36 13.05 K=6
|
| 697 |
+
verify 10: accepted 5/5 (K=6) + correction -> +6 tokens (166.1 ms) cpos=116
|
| 698 |
+
[margins] 10.19 14.47 7.96 1.10 1.75 K=4
|
| 699 |
+
verify 11: accepted 3/3 (K=4) + correction -> +4 tokens (131.9 ms) cpos=120
|
| 700 |
+
[margins] 3.09 1.56 1.42 0.24 3.29 K=3
|
| 701 |
+
verify 12: accepted 1/2 (K=3) + correction -> +2 tokens (114.3 ms) cpos=122
|
| 702 |
+
[margins] 8.35 4.18 7.93 2.96 2.01 K=6
|
| 703 |
+
verify 13: accepted 3/5 (K=6) + correction -> +4 tokens (181.2 ms) cpos=126
|
| 704 |
+
[margins] 12.86 5.66 4.70 10.93 7.44 K=6
|
| 705 |
+
verify 14: accepted 5/5 (K=6) + correction -> +6 tokens (181.0 ms) cpos=132
|
| 706 |
+
[margins] 12.24 14.59 1.62 9.31 9.81 K=6
|
| 707 |
+
verify 15: accepted 2/5 (K=6) + correction -> +3 tokens (158.8 ms) cpos=135
|
| 708 |
+
[margins] 12.92 14.93 9.17 7.25 0.93 K=5
|
| 709 |
+
verify 16: accepted 4/4 (K=5) + correction -> +5 tokens (148.3 ms) cpos=140
|
| 710 |
+
[margins] 7.78 2.13 6.93 0.33 5.57 K=4
|
| 711 |
+
verify 17: accepted 0/3 (K=4) + correction -> +1 tokens (127.9 ms) cpos=141
|
| 712 |
+
[margins] 7.67 5.76 2.76 0.11 1.62 K=4
|
| 713 |
+
verify 18: accepted 2/3 (K=4) + correction -> +3 tokens (128.5 ms) cpos=144
|
| 714 |
+
[margins] 10.85 5.86 4.33 5.05 2.86 K=6
|
| 715 |
+
verify 19: accepted 4/5 (K=6) + correction -> +5 tokens (161.5 ms) cpos=149
|
| 716 |
+
[margins] 13.69 11.24 4.49 6.33 10.06 K=6
|
| 717 |
+
verify 20: accepted 5/5 (K=6) + correction -> +6 tokens (160.7 ms) cpos=155
|
| 718 |
+
[margins] 14.97 10.81 11.49 8.17 1.11 K=5
|
| 719 |
+
verify 21: accepted 4/4 (K=5) + correction -> +5 tokens (148.4 ms) cpos=160
|
| 720 |
+
[margins] 8.21 1.04 10.85 6.02 4.27 K=2
|
| 721 |
+
verify 22: accepted 0/1 (K=2) + correction -> +1 tokens (100.6 ms) cpos=161
|
| 722 |
+
[margins] 9.44 6.04 1.53 4.17 0.87 K=5
|
| 723 |
+
verify 23: accepted 2/4 (K=5) + correction -> +3 tokens (140.7 ms) cpos=164
|
| 724 |
+
[margins] 9.58 7.03 2.74 9.25 6.31 K=6
|
| 725 |
+
verify 24: accepted 5/5 (K=6) + correction -> +6 tokens (161.2 ms) cpos=170
|
| 726 |
+
[margins] 1.52 7.41 10.73 10.58 11.20 K=6
|
| 727 |
+
verify 25: accepted 0/5 (K=6) + correction -> +1 tokens (166.6 ms) cpos=171
|
| 728 |
+
[margins] 1.77 11.35 7.98 1.96 8.53 K=6
|
| 729 |
+
verify 26: accepted 3/5 (K=6) + correction -> +4 tokens (167.1 ms) cpos=175
|
| 730 |
+
[margins] 13.99 13.45 11.89 8.00 1.15 K=5
|
| 731 |
+
verify 27: accepted 4/4 (K=5) + correction -> +5 tokens (149.2 ms) cpos=180
|
| 732 |
+
[margins] 16.37 16.38 5.45 2.80 7.66 K=6
|
| 733 |
+
verify 28: accepted 5/5 (K=6) + correction -> +6 tokens (160.3 ms) cpos=186
|
| 734 |
+
[margins] 5.00 9.08 4.87 7.00 1.55 K=6
|
| 735 |
+
verify 29: accepted 5/5 (K=6) + correction -> +6 tokens (166.6 ms) cpos=192
|
| 736 |
+
[margins] 13.04 16.25 7.42 9.97 11.10 K=6
|
| 737 |
+
verify 30: accepted 5/5 (K=6) + correction -> +6 tokens (161.3 ms) cpos=198
|
| 738 |
+
[margins] 7.97 11.58 11.85 12.80 2.60 K=6
|
| 739 |
+
verify 31: accepted 5/5 (K=6) + correction -> +6 tokens (163.7 ms) cpos=204
|
| 740 |
+
[margins] 9.12 2.91 3.21 6.09 0.97 K=5
|
| 741 |
+
verify 32: accepted 4/4 (K=5) + correction -> +5 tokens (142.6 ms) cpos=209
|
| 742 |
+
[margins] 14.06 11.71 6.65 8.81 11.51 K=6
|
| 743 |
+
verify 33: accepted 5/5 (K=6) + correction -> +6 tokens (161.4 ms) cpos=215
|
| 744 |
+
[margins] 16.08 14.28 10.40 8.70 0.35 K=5
|
| 745 |
+
verify 34: accepted 4/4 (K=5) + correction -> +5 tokens (150.7 ms) cpos=220
|
| 746 |
+
[margins] 19.48 13.46 2.26 0.75 6.07 K=4
|
| 747 |
+
verify 35: accepted 3/3 (K=4) + correction -> +4 tokens (129.3 ms) cpos=224
|
| 748 |
+
[margins] 11.27 4.49 2.60 8.39 1.23 K=5
|
| 749 |
+
verify 36: accepted 4/4 (K=5) + correction -> +5 tokens (144.8 ms) cpos=229
|
| 750 |
+
[margins] 18.88 10.79 7.33 10.19 9.57 K=6
|
| 751 |
+
verify 37: accepted 5/5 (K=6) + correction -> +6 tokens (165.6 ms) cpos=235
|
| 752 |
+
[margins] 7.19 10.65 7.83 5.92 0.85 K=5
|
| 753 |
+
verify 38: accepted 4/4 (K=5) + correction -> +5 tokens (151.2 ms) cpos=240
|
| 754 |
+
[margins] 19.11 14.53 5.12 2.87 6.08 K=6
|
| 755 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (162.2 ms) cpos=246
|
| 756 |
+
[margins] 10.52 5.20 0.76 8.95 10.63 K=3
|
| 757 |
+
verify 40: accepted 2/2 (K=3) + correction -> +3 tokens (122.2 ms) cpos=249
|
| 758 |
+
[margins] 14.68 11.09 6.78 10.81 11.23 K=6
|
| 759 |
+
verify 41: accepted 5/5 (K=6) + correction -> +6 tokens (161.0 ms) cpos=255
|
| 760 |
+
[margins] 14.68 13.66 11.48 7.06 6.84 K=6
|
| 761 |
+
verify 42: accepted 5/5 (K=6) + correction -> +6 tokens (182.5 ms) cpos=261
|
| 762 |
+
[margins] 14.71 9.23 5.94 7.58 1.54 K=6
|
| 763 |
+
verify 43: accepted 4/5 (K=6) + correction -> +5 tokens (162.3 ms) cpos=266
|
| 764 |
+
[margins] 12.39 10.52 1.09 4.89 6.97 K=3
|
| 765 |
+
verify 44: accepted 2/2 (K=3) + correction -> +3 tokens (120.2 ms) cpos=269
|
| 766 |
+
[margins] 14.69 12.46 6.68 10.59 9.66 K=6
|
| 767 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (165.3 ms) cpos=275
|
| 768 |
+
[margins] 13.00 16.06 11.22 8.15 8.80 K=6
|
| 769 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (168.4 ms) cpos=281
|
| 770 |
+
[margins] 14.44 6.50 6.47 7.37 0.36 K=5
|
| 771 |
+
verify 47: accepted 4/4 (K=5) + correction -> +5 tokens (145.3 ms) cpos=286
|
| 772 |
+
|
| 773 |
+
[spec] generated 204 tokens over 47 verifies: mean tokens/verify = 4.34 (block=5, max 6)
|
| 774 |
+
[spec] tokens: 1 50 201 671 15020 4181 362 2775 14817 14922 344 223 25 22765 7975 55 15 3180 16 1 50 201 671 15020 4181 362 2775 14817 14922 344 223 25 22765 7975 55 15 3180 16 1 50
|
| 775 |
+
[spec] SPEC-DECODE: 33.4 ms/tok = 29.94 tok/s (vs base M=1 68.6 ms/tok = 14.59 tok/s -> 2.05x)
|
| 776 |
+
[decode] PREFILL: 14 positions in 285.5 ms = 49.0 tok/s (20.392 ms/tok)
|
| 777 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=6 s=15)...
|
| 778 |
+
[margins] 0.25 4.42 0.71 0.94 0.59 K=3
|
| 779 |
+
verify 1: accepted 1/2 (K=3) + correction -> +2 tokens (115.1 ms) cpos=16
|
| 780 |
+
[margins] 3.22 0.57 1.14 1.92 2.93 K=2
|
| 781 |
+
verify 2: accepted 1/1 (K=2) + correction -> +2 tokens (98.9 ms) cpos=18
|
| 782 |
+
[margins] 2.29 0.38 0.85 2.01 3.46 K=2
|
| 783 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (102.9 ms) cpos=20
|
| 784 |
+
[margins] 2.27 1.12 1.82 2.99 1.82 K=2
|
| 785 |
+
verify 4: accepted 1/1 (K=2) + correction -> +2 tokens (97.5 ms) cpos=22
|
| 786 |
+
[margins] 3.58 1.14 1.97 3.32 2.57 K=2
|
| 787 |
+
verify 5: accepted 1/1 (K=2) + correction -> +2 tokens (101.8 ms) cpos=24
|
| 788 |
+
[margins] 3.14 3.84 1.90 1.15 4.28 K=4
|
| 789 |
+
verify 6: accepted 3/3 (K=4) + correction -> +4 tokens (117.2 ms) cpos=28
|
| 790 |
+
[margins] 2.17 4.72 3.34 2.04 3.00 K=6
|
| 791 |
+
verify 7: accepted 2/5 (K=6) + correction -> +3 tokens (143.5 ms) cpos=31
|
| 792 |
+
[margins] 0.49 3.10 3.63 3.48 0.26 K=5
|
| 793 |
+
verify 8: accepted 0/4 (K=5) + correction -> +1 tokens (137.4 ms) cpos=32
|
| 794 |
+
[margins] 6.77 1.18 0.23 7.44 2.39 K=2
|
| 795 |
+
verify 9: accepted 1/1 (K=2) + correction -> +2 tokens (96.9 ms) cpos=34
|
| 796 |
+
[margins] 2.67 5.87 0.57 0.12 5.66 K=3
|
| 797 |
+
verify 10: accepted 2/2 (K=3) + correction -> +3 tokens (110.3 ms) cpos=37
|
| 798 |
+
[margins] 11.60 6.83 3.32 4.36 6.25 K=6
|
| 799 |
+
verify 11: accepted 5/5 (K=6) + correction -> +6 tokens (148.8 ms) cpos=43
|
| 800 |
+
[margins] 13.34 8.08 8.66 11.85 6.97 K=6
|
| 801 |
+
verify 12: accepted 5/5 (K=6) + correction -> +6 tokens (156.2 ms) cpos=49
|
| 802 |
+
[margins] 14.24 10.58 9.88 10.07 10.45 K=6
|
| 803 |
+
verify 13: accepted 5/5 (K=6) + correction -> +6 tokens (151.9 ms) cpos=55
|
| 804 |
+
[margins] 13.81 9.82 12.52 7.65 9.54 K=6
|
| 805 |
+
verify 14: accepted 5/5 (K=6) + correction -> +6 tokens (155.2 ms) cpos=61
|
| 806 |
+
[margins] 17.49 10.53 12.91 10.16 10.48 K=6
|
| 807 |
+
verify 15: accepted 5/5 (K=6) + correction -> +6 tokens (152.2 ms) cpos=67
|
| 808 |
+
[margins] 16.59 10.84 9.23 10.44 9.02 K=6
|
| 809 |
+
verify 16: accepted 5/5 (K=6) + correction -> +6 tokens (159.2 ms) cpos=73
|
| 810 |
+
[margins] 14.93 11.09 11.95 8.04 9.28 K=6
|
| 811 |
+
verify 17: accepted 5/5 (K=6) + correction -> +6 tokens (153.0 ms) cpos=79
|
| 812 |
+
[margins] 16.19 10.92 12.85 12.61 12.42 K=6
|
| 813 |
+
verify 18: accepted 5/5 (K=6) + correction -> +6 tokens (157.8 ms) cpos=85
|
| 814 |
+
[margins] 14.46 10.88 11.01 11.56 9.83 K=6
|
| 815 |
+
verify 19: accepted 5/5 (K=6) + correction -> +6 tokens (155.5 ms) cpos=91
|
| 816 |
+
[margins] 16.56 11.10 12.72 9.53 11.35 K=6
|
| 817 |
+
verify 20: accepted 5/5 (K=6) + correction -> +6 tokens (161.8 ms) cpos=97
|
| 818 |
+
[margins] 16.74 11.42 13.92 11.04 12.02 K=6
|
| 819 |
+
verify 21: accepted 5/5 (K=6) + correction -> +6 tokens (153.4 ms) cpos=103
|
| 820 |
+
[margins] 13.99 11.07 12.39 12.04 9.34 K=6
|
| 821 |
+
verify 22: accepted 5/5 (K=6) + correction -> +6 tokens (162.1 ms) cpos=109
|
| 822 |
+
[margins] 15.63 10.88 13.10 13.12 10.23 K=6
|
| 823 |
+
verify 23: accepted 5/5 (K=6) + correction -> +6 tokens (156.3 ms) cpos=115
|
| 824 |
+
[margins] 13.26 10.39 13.38 11.83 11.12 K=6
|
| 825 |
+
verify 24: accepted 5/5 (K=6) + correction -> +6 tokens (160.5 ms) cpos=121
|
| 826 |
+
[margins] 14.76 10.59 13.47 9.99 11.08 K=6
|
| 827 |
+
verify 25: accepted 5/5 (K=6) + correction -> +6 tokens (157.7 ms) cpos=127
|
| 828 |
+
[margins] 16.90 11.26 14.16 11.79 10.59 K=6
|
| 829 |
+
verify 26: accepted 5/5 (K=6) + correction -> +6 tokens (176.1 ms) cpos=133
|
| 830 |
+
[margins] 14.92 9.76 13.04 9.45 10.02 K=6
|
| 831 |
+
verify 27: accepted 5/5 (K=6) + correction -> +6 tokens (153.6 ms) cpos=139
|
| 832 |
+
[margins] 13.75 9.82 13.81 12.25 10.47 K=6
|
| 833 |
+
verify 28: accepted 5/5 (K=6) + correction -> +6 tokens (160.7 ms) cpos=145
|
| 834 |
+
[margins] 15.96 9.74 12.75 10.44 9.18 K=6
|
| 835 |
+
verify 29: accepted 5/5 (K=6) + correction -> +6 tokens (156.0 ms) cpos=151
|
| 836 |
+
[margins] 14.86 10.12 13.09 8.78 11.65 K=6
|
| 837 |
+
verify 30: accepted 5/5 (K=6) + correction -> +6 tokens (160.3 ms) cpos=157
|
| 838 |
+
[margins] 14.51 9.35 11.11 12.79 9.11 K=6
|
| 839 |
+
verify 31: accepted 5/5 (K=6) + correction -> +6 tokens (159.2 ms) cpos=163
|
| 840 |
+
[margins] 17.49 10.05 12.74 10.73 8.97 K=6
|
| 841 |
+
verify 32: accepted 5/5 (K=6) + correction -> +6 tokens (160.9 ms) cpos=169
|
| 842 |
+
[margins] 15.84 10.99 13.12 7.96 12.79 K=6
|
| 843 |
+
verify 33: accepted 5/5 (K=6) + correction -> +6 tokens (158.7 ms) cpos=175
|
| 844 |
+
[margins] 15.49 9.94 12.40 6.64 10.56 K=6
|
| 845 |
+
verify 34: accepted 5/5 (K=6) + correction -> +6 tokens (162.2 ms) cpos=181
|
| 846 |
+
[margins] 17.16 10.47 12.95 9.33 11.14 K=6
|
| 847 |
+
verify 35: accepted 5/5 (K=6) + correction -> +6 tokens (158.8 ms) cpos=187
|
| 848 |
+
[margins] 16.75 10.98 13.72 10.89 8.72 K=6
|
| 849 |
+
verify 36: accepted 5/5 (K=6) + correction -> +6 tokens (163.9 ms) cpos=193
|
| 850 |
+
[margins] 16.93 10.23 12.95 10.38 8.27 K=6
|
| 851 |
+
verify 37: accepted 5/5 (K=6) + correction -> +6 tokens (157.7 ms) cpos=199
|
| 852 |
+
[margins] 19.10 10.19 12.96 10.60 7.98 K=6
|
| 853 |
+
verify 38: accepted 5/5 (K=6) + correction -> +6 tokens (163.0 ms) cpos=205
|
| 854 |
+
[margins] 16.51 10.76 13.36 10.81 9.53 K=6
|
| 855 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (158.2 ms) cpos=211
|
| 856 |
+
[margins] 17.49 9.63 12.79 5.35 10.07 K=6
|
| 857 |
+
verify 40: accepted 5/5 (K=6) + correction -> +6 tokens (163.2 ms) cpos=217
|
| 858 |
+
|
| 859 |
+
[spec] generated 203 tokens over 40 verifies: mean tokens/verify = 5.08 (block=5, max 6)
|
| 860 |
+
[spec] tokens: 1 16 1 16 1 16 1 16 1 16 1 16 1 16 1 16 403 31310 16 403 31310 16 403 31310 16 403 31310 16 403 31310 16 403 31310 16 403 31310 16 403 31310 16
|
| 861 |
+
[spec] SPEC-DECODE: 28.7 ms/tok = 34.89 tok/s (vs base M=1 68.6 ms/tok = 14.59 tok/s -> 2.39x)
|
| 862 |
+
[decode] PREFILL: 37 positions in 642.5 ms = 57.6 tok/s (17.364 ms/tok)
|
| 863 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=7 s=38)...
|
| 864 |
+
[margins] 0.90 2.24 0.11 0.27 0.46 K=3
|
| 865 |
+
verify 1: accepted 0/2 (K=3) + correction -> +1 tokens (116.1 ms) cpos=38
|
| 866 |
+
[margins] 0.10 6.02 0.50 1.81 0.24 K=3
|
| 867 |
+
verify 2: accepted 0/2 (K=3) + correction -> +1 tokens (111.4 ms) cpos=39
|
| 868 |
+
[margins] 1.62 0.20 5.08 0.50 0.73 K=2
|
| 869 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (99.4 ms) cpos=41
|
| 870 |
+
[margins] 2.83 0.15 1.53 6.03 0.06 K=2
|
| 871 |
+
verify 4: accepted 1/1 (K=2) + correction -> +2 tokens (95.0 ms) cpos=43
|
| 872 |
+
[margins] 1.13 1.96 0.23 0.05 0.20 K=3
|
| 873 |
+
verify 5: accepted 0/2 (K=3) + correction -> +1 tokens (111.5 ms) cpos=44
|
| 874 |
+
[margins] 0.93 0.11 0.95 0.58 0.51 K=2
|
| 875 |
+
verify 6: accepted 1/1 (K=2) + correction -> +2 tokens (95.3 ms) cpos=46
|
| 876 |
+
[margins] 1.23 0.60 2.10 0.23 1.67 K=2
|
| 877 |
+
verify 7: accepted 0/1 (K=2) + correction -> +1 tokens (100.5 ms) cpos=47
|
| 878 |
+
[margins] 1.98 2.73 0.27 1.36 1.25 K=3
|
| 879 |
+
verify 8: accepted 1/2 (K=3) + correction -> +2 tokens (113.5 ms) cpos=49
|
| 880 |
+
[margins] 8.14 7.45 5.85 2.81 0.95 K=5
|
| 881 |
+
verify 9: accepted 4/4 (K=5) + correction -> +5 tokens (138.0 ms) cpos=54
|
| 882 |
+
[margins] 0.07 0.51 3.32 3.65 2.33 K=2
|
| 883 |
+
verify 10: accepted 1/1 (K=2) + correction -> +2 tokens (101.4 ms) cpos=56
|
| 884 |
+
[margins] 5.32 2.34 1.44 0.50 0.23 K=3
|
| 885 |
+
verify 11: accepted 2/2 (K=3) + correction -> +3 tokens (108.2 ms) cpos=59
|
| 886 |
+
[margins] 3.87 2.80 0.71 0.19 0.17 K=3
|
| 887 |
+
verify 12: accepted 2/2 (K=3) + correction -> +3 tokens (113.4 ms) cpos=62
|
| 888 |
+
[margins] 1.30 0.09 0.12 0.10 0.55 K=2
|
| 889 |
+
verify 13: accepted 1/1 (K=2) + correction -> +2 tokens (102.1 ms) cpos=64
|
| 890 |
+
[margins] 6.59 8.84 2.89 2.77 4.30 K=6
|
| 891 |
+
verify 14: accepted 3/5 (K=6) + correction -> +4 tokens (155.4 ms) cpos=68
|
| 892 |
+
[margins] 5.22 3.18 0.00 0.74 0.71 K=3
|
| 893 |
+
verify 15: accepted 2/2 (K=3) + correction -> +3 tokens (108.9 ms) cpos=71
|
| 894 |
+
[margins] 2.28 2.15 4.05 0.33 1.54 K=4
|
| 895 |
+
verify 16: accepted 3/3 (K=4) + correction -> +4 tokens (124.9 ms) cpos=75
|
| 896 |
+
[margins] 2.78 9.55 1.46 3.24 3.25 K=3
|
| 897 |
+
verify 17: accepted 2/2 (K=3) + correction -> +3 tokens (111.9 ms) cpos=78
|
| 898 |
+
[margins] 8.55 8.33 6.76 7.80 9.39 K=6
|
| 899 |
+
verify 18: accepted 5/5 (K=6) + correction -> +6 tokens (160.2 ms) cpos=84
|
| 900 |
+
[margins] 8.06 9.12 6.77 3.97 0.30 K=5
|
| 901 |
+
verify 19: accepted 4/4 (K=5) + correction -> +5 tokens (141.2 ms) cpos=89
|
| 902 |
+
[margins] 8.30 6.70 4.01 0.88 0.64 K=4
|
| 903 |
+
verify 20: accepted 3/3 (K=4) + correction -> +4 tokens (128.1 ms) cpos=93
|
| 904 |
+
[margins] 4.78 3.63 2.63 1.18 0.38 K=4
|
| 905 |
+
verify 21: accepted 3/3 (K=4) + correction -> +4 tokens (125.8 ms) cpos=97
|
| 906 |
+
[margins] 9.19 13.02 10.49 9.59 4.17 K=6
|
| 907 |
+
verify 22: accepted 5/5 (K=6) + correction -> +6 tokens (159.5 ms) cpos=103
|
| 908 |
+
[margins] 10.06 4.68 2.62 1.37 9.48 K=4
|
| 909 |
+
verify 23: accepted 3/3 (K=4) + correction -> +4 tokens (129.8 ms) cpos=107
|
| 910 |
+
[margins] 4.98 2.65 9.85 0.80 3.91 K=4
|
| 911 |
+
verify 24: accepted 3/3 (K=4) + correction -> +4 tokens (130.7 ms) cpos=111
|
| 912 |
+
[margins] 10.80 6.39 8.33 4.40 7.22 K=6
|
| 913 |
+
verify 25: accepted 5/5 (K=6) + correction -> +6 tokens (167.1 ms) cpos=117
|
| 914 |
+
[margins] 10.69 9.06 3.06 6.98 5.17 K=6
|
| 915 |
+
verify 26: accepted 5/5 (K=6) + correction -> +6 tokens (161.4 ms) cpos=123
|
| 916 |
+
[margins] 14.25 5.24 9.30 8.57 0.13 K=5
|
| 917 |
+
verify 27: accepted 4/4 (K=5) + correction -> +5 tokens (162.2 ms) cpos=128
|
| 918 |
+
[margins] 5.53 5.44 4.11 2.61 2.87 K=6
|
| 919 |
+
verify 28: accepted 3/5 (K=6) + correction -> +4 tokens (160.3 ms) cpos=132
|
| 920 |
+
[margins] 4.96 2.24 3.59 2.65 0.91 K=5
|
| 921 |
+
verify 29: accepted 4/4 (K=5) + correction -> +5 tokens (141.8 ms) cpos=137
|
| 922 |
+
[margins] 2.39 0.36 0.23 0.74 1.09 K=2
|
| 923 |
+
verify 30: accepted 1/1 (K=2) + correction -> +2 tokens (101.8 ms) cpos=139
|
| 924 |
+
[margins] 6.28 0.98 5.60 7.46 5.65 K=2
|
| 925 |
+
verify 31: accepted 1/1 (K=2) + correction -> +2 tokens (104.7 ms) cpos=141
|
| 926 |
+
[margins] 9.96 7.95 5.89 1.56 0.59 K=5
|
| 927 |
+
verify 32: accepted 4/4 (K=5) + correction -> +5 tokens (144.9 ms) cpos=146
|
| 928 |
+
[margins] 7.20 9.85 10.72 12.55 2.23 K=6
|
| 929 |
+
verify 33: accepted 4/5 (K=6) + correction -> +5 tokens (168.0 ms) cpos=151
|
| 930 |
+
[margins] 2.68 1.92 0.54 7.88 0.26 K=3
|
| 931 |
+
verify 34: accepted 1/2 (K=3) + correction -> +2 tokens (122.7 ms) cpos=153
|
| 932 |
+
[margins] 2.43 2.62 0.59 1.61 3.92 K=3
|
| 933 |
+
verify 35: accepted 0/2 (K=3) + correction -> +1 tokens (108.8 ms) cpos=154
|
| 934 |
+
[margins] 6.38 1.89 0.83 3.32 1.64 K=3
|
| 935 |
+
verify 36: accepted 1/2 (K=3) + correction -> +2 tokens (115.7 ms) cpos=156
|
| 936 |
+
[margins] 5.80 3.12 0.25 1.75 1.85 K=3
|
| 937 |
+
verify 37: accepted 1/2 (K=3) + correction -> +2 tokens (109.9 ms) cpos=158
|
| 938 |
+
[margins] 3.76 1.07 2.73 0.34 1.11 K=2
|
| 939 |
+
verify 38: accepted 1/1 (K=2) + correction -> +2 tokens (107.3 ms) cpos=160
|
| 940 |
+
[margins] 4.21 4.35 3.57 0.66 2.46 K=4
|
| 941 |
+
verify 39: accepted 3/3 (K=4) + correction -> +4 tokens (123.6 ms) cpos=164
|
| 942 |
+
[margins] 4.04 9.14 4.30 3.93 4.38 K=6
|
| 943 |
+
verify 40: accepted 5/5 (K=6) + correction -> +6 tokens (149.2 ms) cpos=170
|
| 944 |
+
[margins] 3.42 10.00 3.39 6.18 4.08 K=6
|
| 945 |
+
verify 41: accepted 5/5 (K=6) + correction -> +6 tokens (154.8 ms) cpos=176
|
| 946 |
+
[margins] 3.19 9.88 2.90 7.75 4.63 K=6
|
| 947 |
+
verify 42: accepted 5/5 (K=6) + correction -> +6 tokens (150.2 ms) cpos=182
|
| 948 |
+
[margins] 2.21 9.64 4.14 6.78 5.27 K=6
|
| 949 |
+
verify 43: accepted 5/5 (K=6) + correction -> +6 tokens (155.5 ms) cpos=188
|
| 950 |
+
[margins] 1.39 9.14 4.18 6.29 4.95 K=6
|
| 951 |
+
verify 44: accepted 5/5 (K=6) + correction -> +6 tokens (150.1 ms) cpos=194
|
| 952 |
+
[margins] 0.97 9.17 3.51 6.29 4.72 K=6
|
| 953 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (155.4 ms) cpos=200
|
| 954 |
+
[margins] 1.45 9.81 3.84 5.34 4.26 K=6
|
| 955 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (150.4 ms) cpos=206
|
| 956 |
+
[margins] 1.91 8.81 3.53 5.06 5.15 K=6
|
| 957 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (156.2 ms) cpos=212
|
| 958 |
+
[margins] 2.59 8.61 3.35 4.86 4.77 K=6
|
| 959 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (148.9 ms) cpos=218
|
| 960 |
+
[margins] 2.78 8.38 4.41 4.10 4.96 K=6
|
| 961 |
+
verify 49: accepted 5/5 (K=6) + correction -> +6 tokens (156.2 ms) cpos=224
|
| 962 |
+
[margins] 2.94 8.82 3.58 4.41 4.62 K=6
|
| 963 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (150.1 ms) cpos=230
|
| 964 |
+
[margins] 2.74 8.39 4.09 2.96 4.43 K=6
|
| 965 |
+
verify 51: accepted 0/5 (K=6) + correction -> +1 tokens (156.3 ms) cpos=231
|
| 966 |
+
[margins] 8.66 0.97 5.34 4.16 2.21 K=2
|
| 967 |
+
verify 52: accepted 0/1 (K=2) + correction -> +1 tokens (104.3 ms) cpos=232
|
| 968 |
+
[margins] 5.92 2.53 7.56 1.29 0.11 K=4
|
| 969 |
+
verify 53: accepted 1/3 (K=4) + correction -> +2 tokens (126.5 ms) cpos=234
|
| 970 |
+
[margins] 2.77 1.24 3.19 1.19 0.19 K=2
|
| 971 |
+
verify 54: accepted 1/1 (K=2) + correction -> +2 tokens (104.1 ms) cpos=236
|
| 972 |
+
[margins] 2.99 0.70 6.03 0.88 0.37 K=2
|
| 973 |
+
verify 55: accepted 0/1 (K=2) + correction -> +1 tokens (100.9 ms) cpos=237
|
| 974 |
+
|
| 975 |
+
[spec] generated 200 tokens over 55 verifies: mean tokens/verify = 3.64 (block=5, max 6)
|
| 976 |
+
[spec] tokens: 343 12888 28 566 344 260 19075 3417 9508 5718 270 2753 294 270 6616 366 1512 1527 27819 13459 16 5715 270 12919 6329 1512 1527 940 223 19 27819 13459 16 455 3452 2753 344 979 7490 201
|
| 977 |
+
[spec] SPEC-DECODE: 35.4 ms/tok = 28.28 tok/s (vs base M=1 68.6 ms/tok = 14.59 tok/s -> 1.94x)
|
| 978 |
+
[decode] PREFILL: 12 positions in 250.5 ms = 47.9 tok/s (20.878 ms/tok)
|
| 979 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=8 s=13)...
|
| 980 |
+
[margins] 3.14 0.86 0.12 0.69 1.59 K=2
|
| 981 |
+
verify 1: accepted 1/1 (K=2) + correction -> +2 tokens (98.4 ms) cpos=14
|
| 982 |
+
[margins] 0.08 6.14 3.02 0.67 6.14 K=4
|
| 983 |
+
verify 2: accepted 0/3 (K=4) + correction -> +1 tokens (127.3 ms) cpos=15
|
| 984 |
+
[margins] 0.91 0.83 1.56 1.83 0.16 K=2
|
| 985 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (101.9 ms) cpos=17
|
| 986 |
+
[margins] 0.82 0.35 0.44 2.75 0.13 K=2
|
| 987 |
+
verify 4: accepted 1/1 (K=2) + correction -> +2 tokens (98.4 ms) cpos=19
|
| 988 |
+
[margins] 2.77 0.40 1.11 0.12 3.15 K=2
|
| 989 |
+
verify 5: accepted 1/1 (K=2) + correction -> +2 tokens (101.7 ms) cpos=21
|
| 990 |
+
[margins] 2.92 0.11 1.70 0.23 3.41 K=2
|
| 991 |
+
verify 6: accepted 1/1 (K=2) + correction -> +2 tokens (97.8 ms) cpos=23
|
| 992 |
+
[margins] 3.26 0.11 0.65 0.24 3.60 K=2
|
| 993 |
+
verify 7: accepted 1/1 (K=2) + correction -> +2 tokens (101.9 ms) cpos=25
|
| 994 |
+
[margins] 4.15 0.28 1.54 0.11 4.26 K=2
|
| 995 |
+
verify 8: accepted 1/1 (K=2) + correction -> +2 tokens (98.2 ms) cpos=27
|
| 996 |
+
[margins] 5.13 0.24 1.91 0.44 5.05 K=2
|
| 997 |
+
verify 9: accepted 1/1 (K=2) + correction -> +2 tokens (102.0 ms) cpos=29
|
| 998 |
+
[margins] 5.82 0.44 2.75 0.43 4.48 K=2
|
| 999 |
+
verify 10: accepted 1/1 (K=2) + correction -> +2 tokens (98.2 ms) cpos=31
|
| 1000 |
+
[margins] 5.75 0.02 4.17 0.89 4.33 K=2
|
| 1001 |
+
verify 11: accepted 1/1 (K=2) + correction -> +2 tokens (102.2 ms) cpos=33
|
| 1002 |
+
[margins] 5.61 0.12 4.29 0.63 3.96 K=2
|
| 1003 |
+
verify 12: accepted 1/1 (K=2) + correction -> +2 tokens (98.5 ms) cpos=35
|
| 1004 |
+
[margins] 6.12 0.08 5.58 0.61 4.70 K=2
|
| 1005 |
+
verify 13: accepted 1/1 (K=2) + correction -> +2 tokens (102.2 ms) cpos=37
|
| 1006 |
+
[margins] 5.75 0.02 6.25 0.29 4.04 K=2
|
| 1007 |
+
verify 14: accepted 1/1 (K=2) + correction -> +2 tokens (98.6 ms) cpos=39
|
| 1008 |
+
[margins] 6.58 0.36 7.45 0.38 4.84 K=2
|
| 1009 |
+
verify 15: accepted 1/1 (K=2) + correction -> +2 tokens (102.4 ms) cpos=41
|
| 1010 |
+
[margins] 6.14 0.37 5.41 0.61 4.06 K=2
|
| 1011 |
+
verify 16: accepted 1/1 (K=2) + correction -> +2 tokens (99.2 ms) cpos=43
|
| 1012 |
+
[margins] 6.96 0.53 6.08 1.09 4.41 K=2
|
| 1013 |
+
verify 17: accepted 1/1 (K=2) + correction -> +2 tokens (102.9 ms) cpos=45
|
| 1014 |
+
[margins] 5.95 1.26 4.55 0.74 3.41 K=2
|
| 1015 |
+
verify 18: accepted 0/1 (K=2) + correction -> +1 tokens (95.9 ms) cpos=46
|
| 1016 |
+
[margins] 5.36 3.16 6.41 0.01 0.50 K=4
|
| 1017 |
+
verify 19: accepted 3/3 (K=4) + correction -> +4 tokens (125.8 ms) cpos=50
|
| 1018 |
+
[margins] 2.74 2.29 0.61 1.90 3.94 K=3
|
| 1019 |
+
verify 20: accepted 2/2 (K=3) + correction -> +3 tokens (113.3 ms) cpos=53
|
| 1020 |
+
[margins] 6.77 8.82 0.32 1.08 1.52 K=3
|
| 1021 |
+
verify 21: accepted 2/2 (K=3) + correction -> +3 tokens (111.6 ms) cpos=56
|
| 1022 |
+
[margins] 3.10 1.80 1.56 2.61 2.99 K=6
|
| 1023 |
+
verify 22: accepted 2/5 (K=6) + correction -> +3 tokens (152.3 ms) cpos=59
|
| 1024 |
+
[margins] 1.77 1.82 3.71 5.28 0.31 K=5
|
| 1025 |
+
verify 23: accepted 0/4 (K=5) + correction -> +1 tokens (139.5 ms) cpos=60
|
| 1026 |
+
[margins] 5.89 4.03 5.48 6.96 2.77 K=6
|
| 1027 |
+
verify 24: accepted 5/5 (K=6) + correction -> +6 tokens (154.5 ms) cpos=66
|
| 1028 |
+
[margins] 7.39 10.81 8.44 1.98 0.79 K=5
|
| 1029 |
+
verify 25: accepted 3/4 (K=5) + correction -> +4 tokens (140.4 ms) cpos=70
|
| 1030 |
+
[margins] 2.23 4.21 0.58 4.72 2.06 K=3
|
| 1031 |
+
verify 26: accepted 0/2 (K=3) + correction -> +1 tokens (115.1 ms) cpos=71
|
| 1032 |
+
[margins] 0.16 3.48 3.56 2.89 1.67 K=6
|
| 1033 |
+
verify 27: accepted 0/5 (K=6) + correction -> +1 tokens (159.4 ms) cpos=72
|
| 1034 |
+
[margins] 2.66 3.28 4.26 6.14 2.85 K=6
|
| 1035 |
+
verify 28: accepted 5/5 (K=6) + correction -> +6 tokens (155.8 ms) cpos=78
|
| 1036 |
+
[margins] 5.85 8.12 6.17 0.03 0.93 K=4
|
| 1037 |
+
verify 29: accepted 3/3 (K=4) + correction -> +4 tokens (128.4 ms) cpos=82
|
| 1038 |
+
[margins] 3.80 6.93 4.12 5.12 2.08 K=6
|
| 1039 |
+
verify 30: accepted 5/5 (K=6) + correction -> +6 tokens (162.2 ms) cpos=88
|
| 1040 |
+
[margins] 2.34 6.57 1.20 7.30 0.76 K=3
|
| 1041 |
+
verify 31: accepted 2/2 (K=3) + correction -> +3 tokens (111.8 ms) cpos=91
|
| 1042 |
+
[margins] 3.94 13.01 0.78 2.76 4.42 K=3
|
| 1043 |
+
verify 32: accepted 2/2 (K=3) + correction -> +3 tokens (115.7 ms) cpos=94
|
| 1044 |
+
[margins] 4.92 8.46 8.46 5.81 3.65 K=6
|
| 1045 |
+
verify 33: accepted 5/5 (K=6) + correction -> +6 tokens (164.8 ms) cpos=100
|
| 1046 |
+
[margins] 5.29 7.88 3.85 7.03 1.45 K=5
|
| 1047 |
+
verify 34: accepted 4/4 (K=5) + correction -> +5 tokens (143.2 ms) cpos=105
|
| 1048 |
+
[margins] 2.32 4.73 3.71 6.06 6.22 K=6
|
| 1049 |
+
verify 35: accepted 5/5 (K=6) + correction -> +6 tokens (158.3 ms) cpos=111
|
| 1050 |
+
[margins] 7.38 4.36 1.80 1.55 6.08 K=6
|
| 1051 |
+
verify 36: accepted 5/5 (K=6) + correction -> +6 tokens (164.2 ms) cpos=117
|
| 1052 |
+
[margins] 3.15 6.52 4.22 8.44 7.61 K=6
|
| 1053 |
+
verify 37: accepted 5/5 (K=6) + correction -> +6 tokens (158.3 ms) cpos=123
|
| 1054 |
+
[margins] 11.24 4.79 10.20 6.33 12.11 K=6
|
| 1055 |
+
verify 38: accepted 5/5 (K=6) + correction -> +6 tokens (179.2 ms) cpos=129
|
| 1056 |
+
[margins] 3.91 5.10 7.09 7.39 4.58 K=6
|
| 1057 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (161.6 ms) cpos=135
|
| 1058 |
+
[margins] 10.83 6.33 10.14 5.56 9.80 K=6
|
| 1059 |
+
verify 40: accepted 5/5 (K=6) + correction -> +6 tokens (168.5 ms) cpos=141
|
| 1060 |
+
[margins] 3.67 6.98 3.33 8.54 6.88 K=6
|
| 1061 |
+
verify 41: accepted 5/5 (K=6) + correction -> +6 tokens (161.2 ms) cpos=147
|
| 1062 |
+
[margins] 9.98 2.49 4.75 2.90 7.73 K=6
|
| 1063 |
+
verify 42: accepted 5/5 (K=6) + correction -> +6 tokens (167.1 ms) cpos=153
|
| 1064 |
+
[margins] 2.75 7.37 6.80 6.38 5.22 K=6
|
| 1065 |
+
verify 43: accepted 5/5 (K=6) + correction -> +6 tokens (161.8 ms) cpos=159
|
| 1066 |
+
[margins] 8.03 4.03 3.35 2.89 9.59 K=6
|
| 1067 |
+
verify 44: accepted 5/5 (K=6) + correction -> +6 tokens (165.9 ms) cpos=165
|
| 1068 |
+
[margins] 3.55 5.71 3.57 7.79 7.62 K=6
|
| 1069 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (160.1 ms) cpos=171
|
| 1070 |
+
[margins] 10.88 6.37 9.15 5.15 10.63 K=6
|
| 1071 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (167.3 ms) cpos=177
|
| 1072 |
+
[margins] 4.23 5.06 4.40 7.36 8.68 K=6
|
| 1073 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (159.7 ms) cpos=183
|
| 1074 |
+
[margins] 10.42 6.43 11.57 4.39 13.03 K=6
|
| 1075 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (168.2 ms) cpos=189
|
| 1076 |
+
[margins] 4.50 5.78 7.52 8.69 8.14 K=6
|
| 1077 |
+
verify 49: accepted 5/5 (K=6) + correction -> +6 tokens (160.4 ms) cpos=195
|
| 1078 |
+
[margins] 11.28 6.24 11.15 8.14 8.30 K=6
|
| 1079 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (167.7 ms) cpos=201
|
| 1080 |
+
[margins] 4.24 5.55 5.98 8.11 5.82 K=6
|
| 1081 |
+
verify 51: accepted 5/5 (K=6) + correction -> +6 tokens (161.5 ms) cpos=207
|
| 1082 |
+
[margins] 11.87 6.54 12.01 9.27 9.55 K=6
|
| 1083 |
+
verify 52: accepted 5/5 (K=6) + correction -> +6 tokens (167.5 ms) cpos=213
|
| 1084 |
+
|
| 1085 |
+
[spec] generated 201 tokens over 52 verifies: mean tokens/verify = 3.87 (block=5, max 6)
|
| 1086 |
+
[spec] tokens: 1 201 1 201 1 201 1 201 1 201 1 201 1 201 1 201 1 201 1 201 1 201 1 201 1 201 1 201 1 201 1 201 3085 344 270 6102 294 8760 33 9361
|
| 1087 |
+
[spec] SPEC-DECODE: 34.6 ms/tok = 28.92 tok/s (vs base M=1 68.6 ms/tok = 14.59 tok/s -> 1.98x)
|
| 1088 |
+
|
| 1089 |
+
[blksweep] BLK passes adaptK->eff prompt | mean tok/verify | ms/tok | tok/s | vs base 14.59 tok/s
|
| 1090 |
+
[blksweep] 5 1 1.50 1.50 0 | 3.30 | 39.2 | 25.49 | 1.75x
|
| 1091 |
+
[blksweep] 5 1 1.50 1.50 1 | 4.25 | 33.1 | 30.20 | 2.07x
|
| 1092 |
+
[blksweep] 5 1 1.50 1.50 2 | 4.00 | 34.9 | 28.62 | 1.96x
|
| 1093 |
+
[blksweep] 5 1 1.50 1.50 3 | 2.52 | 47.1 | 21.24 | 1.46x
|
| 1094 |
+
[blksweep] 5 1 1.50 1.50 4 | 3.04 | 40.8 | 24.53 | 1.68x
|
| 1095 |
+
[blksweep] 5 1 1.50 1.50 5 | 4.34 | 33.4 | 29.94 | 2.05x
|
| 1096 |
+
[blksweep] 5 1 1.50 1.50 6 | 5.08 | 28.7 | 34.89 | 2.39x
|
| 1097 |
+
[blksweep] 5 1 1.50 1.50 7 | 3.64 | 35.4 | 28.28 | 1.94x
|
| 1098 |
+
[blksweep] 5 1 1.50 1.50 8 | 3.87 | 34.6 | 28.92 | 1.98x
|
| 1099 |
+
[decode] mem 106.9/122.8 GiB
|