archive auto-ace0p3: eval.log
Browse files- arms/auto-ace0p3/eval.log +1097 -0
arms/auto-ace0p3/eval.log
ADDED
|
@@ -0,0 +1,1097 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 106.7/122.8 GiB
|
| 6 |
+
[decode] prefill 5 positions...
|
| 7 |
+
[f32mk] tile 4x4 (DSV4_F32MK_TILE=unset)
|
| 8 |
+
[decode] PREFILL: 5 positions in 202.0 ms = 24.8 tok/s (40.403 ms/tok)
|
| 9 |
+
[decode] prefill done. caches populated. starting decode.
|
| 10 |
+
step 0 pos 5 -> token 11111 (69.5 ms warmup)
|
| 11 |
+
step 1 pos 6 -> token 16 (69.6 ms)
|
| 12 |
+
step 2 pos 7 -> token 455 (76.1 ms)
|
| 13 |
+
step 3 pos 8 -> token 6102 (69.2 ms)
|
| 14 |
+
step 4 pos 9 -> token 294 (70.0 ms)
|
| 15 |
+
step 5 pos 10 -> token 16603 (70.8 ms)
|
| 16 |
+
step 6 pos 11 -> token 344 (75.3 ms)
|
| 17 |
+
step 7 pos 12 -> token 29168 (69.5 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: 71.5 ms/tok = 13.99 tok/s (M=1 steady state, 7-step avg)
|
| 22 |
+
|
| 23 |
+
[spec-verify] M=5 verify in ONE forward: 121.3 ms (= 24.3 ms/tok if all accepted vs 71.5 M=1 -> 2.95x)
|
| 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-ace0p3/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 112.9/122.8 GiB
|
| 32 |
+
[decode] PREFILL: 5 positions in 141.0 ms = 35.5 tok/s (28.198 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] 1.93 0.92 0.64 0.66 0.65 K=2
|
| 36 |
+
verify 1: accepted 1/1 (K=2) + correction -> +2 tokens (108.3 ms) cpos=7
|
| 37 |
+
[margins] 0.05 0.67 0.35 0.66 0.11 K=2
|
| 38 |
+
verify 2: accepted 0/1 (K=2) + correction -> +1 tokens (114.9 ms) cpos=8
|
| 39 |
+
[margins] 1.48 0.41 1.95 0.46 0.13 K=2
|
| 40 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (109.4 ms) cpos=10
|
| 41 |
+
[margins] 2.02 0.33 3.81 0.58 0.78 K=2
|
| 42 |
+
verify 4: accepted 0/1 (K=2) + correction -> +1 tokens (102.2 ms) cpos=11
|
| 43 |
+
[margins] 6.43 0.16 0.79 1.83 2.42 K=2
|
| 44 |
+
verify 5: accepted 1/1 (K=2) + correction -> +2 tokens (102.9 ms) cpos=13
|
| 45 |
+
[margins] 4.25 2.68 5.44 2.00 0.37 K=5
|
| 46 |
+
verify 6: accepted 4/4 (K=5) + correction -> +5 tokens (140.4 ms) cpos=18
|
| 47 |
+
[margins] 4.69 1.79 2.77 0.68 0.60 K=4
|
| 48 |
+
verify 7: accepted 1/3 (K=4) + correction -> +2 tokens (126.5 ms) cpos=20
|
| 49 |
+
[margins] 2.63 2.42 5.03 1.52 1.11 K=5
|
| 50 |
+
verify 8: accepted 4/4 (K=5) + correction -> +5 tokens (139.4 ms) cpos=25
|
| 51 |
+
[margins] 6.57 1.87 2.30 2.74 3.31 K=6
|
| 52 |
+
verify 9: accepted 1/5 (K=6) + correction -> +2 tokens (157.9 ms) cpos=27
|
| 53 |
+
[margins] 3.73 3.49 6.10 2.42 0.32 K=5
|
| 54 |
+
verify 10: accepted 4/4 (K=5) + correction -> +5 tokens (145.0 ms) cpos=32
|
| 55 |
+
[margins] 6.85 1.06 3.63 1.80 2.37 K=2
|
| 56 |
+
verify 11: accepted 1/1 (K=2) + correction -> +2 tokens (96.2 ms) cpos=34
|
| 57 |
+
[margins] 2.16 4.09 4.96 1.59 0.31 K=5
|
| 58 |
+
verify 12: accepted 4/4 (K=5) + correction -> +5 tokens (140.8 ms) cpos=39
|
| 59 |
+
[margins] 4.35 0.52 4.48 3.03 3.05 K=2
|
| 60 |
+
verify 13: accepted 1/1 (K=2) + correction -> +2 tokens (101.2 ms) cpos=41
|
| 61 |
+
[margins] 3.73 3.93 6.36 1.35 1.67 K=4
|
| 62 |
+
verify 14: accepted 3/3 (K=4) + correction -> +4 tokens (126.7 ms) cpos=45
|
| 63 |
+
[margins] 2.82 0.52 6.46 1.69 4.32 K=2
|
| 64 |
+
verify 15: accepted 1/1 (K=2) + correction -> +2 tokens (97.0 ms) cpos=47
|
| 65 |
+
[margins] 0.93 4.06 0.13 0.11 0.23 K=3
|
| 66 |
+
verify 16: accepted 2/2 (K=3) + correction -> +3 tokens (112.5 ms) cpos=50
|
| 67 |
+
[margins] 4.61 3.94 4.57 0.85 2.11 K=4
|
| 68 |
+
verify 17: accepted 3/3 (K=4) + correction -> +4 tokens (131.1 ms) cpos=54
|
| 69 |
+
[margins] 2.60 1.52 6.38 0.04 2.93 K=4
|
| 70 |
+
verify 18: accepted 3/3 (K=4) + correction -> +4 tokens (128.7 ms) cpos=58
|
| 71 |
+
[margins] 0.19 5.65 5.71 6.51 1.08 K=5
|
| 72 |
+
verify 19: accepted 0/4 (K=5) + correction -> +1 tokens (141.9 ms) cpos=59
|
| 73 |
+
[margins] 5.04 6.74 6.69 0.35 4.25 K=4
|
| 74 |
+
verify 20: accepted 3/3 (K=4) + correction -> +4 tokens (129.8 ms) cpos=63
|
| 75 |
+
[margins] 0.51 0.79 6.53 0.27 3.63 K=2
|
| 76 |
+
verify 21: accepted 0/1 (K=2) + correction -> +1 tokens (102.5 ms) cpos=64
|
| 77 |
+
[margins] 6.57 0.72 2.93 2.08 4.32 K=2
|
| 78 |
+
verify 22: accepted 1/1 (K=2) + correction -> +2 tokens (98.3 ms) cpos=66
|
| 79 |
+
[margins] 4.62 5.43 5.69 2.10 0.40 K=5
|
| 80 |
+
verify 23: accepted 4/4 (K=5) + correction -> +5 tokens (142.8 ms) cpos=71
|
| 81 |
+
[margins] 6.85 1.66 2.43 1.03 2.12 K=4
|
| 82 |
+
verify 24: accepted 3/3 (K=4) + correction -> +4 tokens (130.0 ms) cpos=75
|
| 83 |
+
[margins] 8.05 6.01 2.54 0.45 0.76 K=4
|
| 84 |
+
verify 25: accepted 2/3 (K=4) + correction -> +3 tokens (128.2 ms) cpos=78
|
| 85 |
+
[margins] 5.87 0.10 1.20 4.63 2.70 K=2
|
| 86 |
+
verify 26: accepted 1/1 (K=2) + correction -> +2 tokens (103.8 ms) cpos=80
|
| 87 |
+
[margins] 5.01 6.46 5.65 2.71 0.20 K=5
|
| 88 |
+
verify 27: accepted 4/4 (K=5) + correction -> +5 tokens (144.0 ms) cpos=85
|
| 89 |
+
[margins] 7.40 1.13 1.23 3.62 4.00 K=2
|
| 90 |
+
verify 28: accepted 1/1 (K=2) + correction -> +2 tokens (99.7 ms) cpos=87
|
| 91 |
+
[margins] 4.98 6.44 7.88 1.72 2.67 K=6
|
| 92 |
+
verify 29: accepted 4/5 (K=6) + correction -> +5 tokens (166.6 ms) cpos=92
|
| 93 |
+
[margins] 6.92 0.53 0.52 3.07 4.43 K=2
|
| 94 |
+
verify 30: accepted 1/1 (K=2) + correction -> +2 tokens (101.2 ms) cpos=94
|
| 95 |
+
[margins] 5.15 7.90 5.26 3.04 2.19 K=6
|
| 96 |
+
verify 31: accepted 4/5 (K=6) + correction -> +5 tokens (167.9 ms) cpos=99
|
| 97 |
+
[margins] 5.84 2.05 0.90 2.60 4.06 K=3
|
| 98 |
+
verify 32: accepted 1/2 (K=3) + correction -> +2 tokens (119.0 ms) cpos=101
|
| 99 |
+
[margins] 6.20 6.01 5.59 1.14 2.39 K=4
|
| 100 |
+
verify 33: accepted 3/3 (K=4) + correction -> +4 tokens (131.4 ms) cpos=105
|
| 101 |
+
[margins] 1.38 6.86 0.38 5.61 3.63 K=3
|
| 102 |
+
verify 34: accepted 2/2 (K=3) + correction -> +3 tokens (118.1 ms) cpos=108
|
| 103 |
+
[margins] 6.78 5.31 6.11 2.91 1.73 K=6
|
| 104 |
+
verify 35: accepted 4/5 (K=6) + correction -> +5 tokens (162.8 ms) cpos=113
|
| 105 |
+
[margins] 7.25 1.26 0.66 3.71 2.64 K=2
|
| 106 |
+
verify 36: accepted 1/1 (K=2) + correction -> +2 tokens (102.1 ms) cpos=115
|
| 107 |
+
[margins] 4.18 3.23 7.28 1.93 0.92 K=5
|
| 108 |
+
verify 37: accepted 4/4 (K=5) + correction -> +5 tokens (149.7 ms) cpos=120
|
| 109 |
+
[margins] 6.96 1.26 0.44 2.16 2.45 K=2
|
| 110 |
+
verify 38: accepted 1/1 (K=2) + correction -> +2 tokens (101.9 ms) cpos=122
|
| 111 |
+
[margins] 5.72 5.36 5.66 4.14 1.10 K=5
|
| 112 |
+
verify 39: accepted 4/4 (K=5) + correction -> +5 tokens (145.4 ms) cpos=127
|
| 113 |
+
[margins] 8.02 0.83 0.86 4.16 4.46 K=2
|
| 114 |
+
verify 40: accepted 1/1 (K=2) + correction -> +2 tokens (119.4 ms) cpos=129
|
| 115 |
+
[margins] 7.47 6.61 7.95 1.66 1.77 K=6
|
| 116 |
+
verify 41: accepted 4/5 (K=6) + correction -> +5 tokens (163.4 ms) cpos=134
|
| 117 |
+
[margins] 7.72 1.35 0.93 2.07 3.64 K=2
|
| 118 |
+
verify 42: accepted 1/1 (K=2) + correction -> +2 tokens (107.9 ms) cpos=136
|
| 119 |
+
[margins] 7.30 6.74 6.18 2.21 0.63 K=5
|
| 120 |
+
verify 43: accepted 4/4 (K=5) + correction -> +5 tokens (144.8 ms) cpos=141
|
| 121 |
+
[margins] 5.16 7.66 3.96 2.09 3.82 K=6
|
| 122 |
+
verify 44: accepted 3/5 (K=6) + correction -> +4 tokens (158.9 ms) cpos=145
|
| 123 |
+
[margins] 6.87 6.13 7.75 1.75 1.49 K=5
|
| 124 |
+
verify 45: accepted 4/4 (K=5) + correction -> +5 tokens (144.3 ms) cpos=150
|
| 125 |
+
[margins] 6.68 0.42 1.62 5.83 5.12 K=2
|
| 126 |
+
verify 46: accepted 1/1 (K=2) + correction -> +2 tokens (105.3 ms) cpos=152
|
| 127 |
+
[margins] 15.19 2.99 6.72 7.16 9.43 K=6
|
| 128 |
+
verify 47: accepted 1/5 (K=6) + correction -> +2 tokens (161.7 ms) cpos=154
|
| 129 |
+
[margins] 3.83 8.25 7.69 4.74 2.41 K=6
|
| 130 |
+
verify 48: accepted 4/5 (K=6) + correction -> +5 tokens (166.5 ms) cpos=159
|
| 131 |
+
[margins] 4.17 0.64 3.32 2.54 5.93 K=2
|
| 132 |
+
verify 49: accepted 1/1 (K=2) + correction -> +2 tokens (105.6 ms) cpos=161
|
| 133 |
+
[margins] 9.98 6.07 8.08 7.74 3.44 K=6
|
| 134 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (163.6 ms) cpos=167
|
| 135 |
+
[margins] 6.60 0.93 2.96 4.83 4.44 K=2
|
| 136 |
+
verify 51: accepted 1/1 (K=2) + correction -> +2 tokens (105.4 ms) cpos=169
|
| 137 |
+
[margins] 2.65 5.60 6.49 3.43 2.64 K=6
|
| 138 |
+
verify 52: accepted 4/5 (K=6) + correction -> +5 tokens (160.9 ms) cpos=174
|
| 139 |
+
[margins] 4.21 1.72 1.07 4.00 5.38 K=3
|
| 140 |
+
verify 53: accepted 1/2 (K=3) + correction -> +2 tokens (117.6 ms) cpos=176
|
| 141 |
+
[margins] 4.27 5.34 7.41 2.14 0.20 K=5
|
| 142 |
+
verify 54: accepted 4/4 (K=5) + correction -> +5 tokens (144.8 ms) cpos=181
|
| 143 |
+
[margins] 6.34 1.36 0.18 1.07 6.11 K=2
|
| 144 |
+
verify 55: accepted 1/1 (K=2) + correction -> +2 tokens (102.4 ms) cpos=183
|
| 145 |
+
[margins] 3.64 6.53 8.43 3.05 0.91 K=5
|
| 146 |
+
verify 56: accepted 4/4 (K=5) + correction -> +5 tokens (151.5 ms) cpos=188
|
| 147 |
+
[margins] 1.25 0.14 2.21 0.20 6.22 K=2
|
| 148 |
+
verify 57: accepted 1/1 (K=2) + correction -> +2 tokens (102.6 ms) cpos=190
|
| 149 |
+
[margins] 8.40 2.21 0.37 3.60 2.92 K=3
|
| 150 |
+
verify 58: accepted 1/2 (K=3) + correction -> +2 tokens (118.7 ms) cpos=192
|
| 151 |
+
[margins] 5.61 2.78 5.98 5.72 8.63 K=6
|
| 152 |
+
verify 59: accepted 5/5 (K=6) + correction -> +6 tokens (162.6 ms) cpos=198
|
| 153 |
+
[margins] 1.03 5.61 0.78 1.26 3.18 K=3
|
| 154 |
+
verify 60: accepted 2/2 (K=3) + correction -> +3 tokens (119.6 ms) cpos=201
|
| 155 |
+
[margins] 6.20 7.65 8.81 7.77 1.15 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: 38.9 ms/tok = 25.74 tok/s (vs base M=1 71.5 ms/tok = 13.99 tok/s -> 1.84x)
|
| 162 |
+
[decode] PREFILL: 34 positions in 605.2 ms = 56.2 tok/s (17.800 ms/tok)
|
| 163 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=1 s=35)...
|
| 164 |
+
[margins] 1.60 1.07 1.36 2.10 0.21 K=2
|
| 165 |
+
verify 1: accepted 0/1 (K=2) + correction -> +1 tokens (104.2 ms) cpos=35
|
| 166 |
+
[margins] 3.64 2.99 1.47 1.93 4.56 K=3
|
| 167 |
+
verify 2: accepted 0/2 (K=3) + correction -> +1 tokens (111.8 ms) cpos=36
|
| 168 |
+
[margins] 1.06 1.31 0.28 3.26 0.88 K=2
|
| 169 |
+
verify 3: accepted 0/1 (K=2) + correction -> +1 tokens (95.5 ms) cpos=37
|
| 170 |
+
[margins] 1.74 2.40 1.85 1.57 0.67 K=5
|
| 171 |
+
verify 4: accepted 2/4 (K=5) + correction -> +3 tokens (135.9 ms) cpos=40
|
| 172 |
+
[margins] 0.09 0.42 1.15 0.33 0.80 K=2
|
| 173 |
+
verify 5: accepted 0/1 (K=2) + correction -> +1 tokens (97.8 ms) cpos=41
|
| 174 |
+
[margins] 1.14 4.48 0.14 0.47 0.49 K=3
|
| 175 |
+
verify 6: accepted 2/2 (K=3) + correction -> +3 tokens (112.3 ms) cpos=44
|
| 176 |
+
[margins] 0.13 5.55 10.60 2.42 0.25 K=5
|
| 177 |
+
verify 7: accepted 4/4 (K=5) + correction -> +5 tokens (138.0 ms) cpos=49
|
| 178 |
+
[margins] 5.97 1.34 1.61 0.47 0.51 K=2
|
| 179 |
+
verify 8: accepted 1/1 (K=2) + correction -> +2 tokens (95.7 ms) cpos=51
|
| 180 |
+
[margins] 0.96 1.11 3.81 4.85 3.42 K=2
|
| 181 |
+
verify 9: accepted 0/1 (K=2) + correction -> +1 tokens (101.4 ms) cpos=52
|
| 182 |
+
[margins] 3.89 4.60 6.66 1.39 1.12 K=4
|
| 183 |
+
verify 10: accepted 3/3 (K=4) + correction -> +4 tokens (127.5 ms) cpos=56
|
| 184 |
+
[margins] 3.45 1.31 0.47 1.57 2.10 K=2
|
| 185 |
+
verify 11: accepted 1/1 (K=2) + correction -> +2 tokens (102.0 ms) cpos=58
|
| 186 |
+
[margins] 2.47 3.06 3.27 0.14 3.52 K=4
|
| 187 |
+
verify 12: accepted 0/3 (K=4) + correction -> +1 tokens (116.1 ms) cpos=59
|
| 188 |
+
[margins] 0.75 0.49 3.11 0.24 1.30 K=2
|
| 189 |
+
verify 13: accepted 0/1 (K=2) + correction -> +1 tokens (102.0 ms) cpos=60
|
| 190 |
+
[margins] 0.77 1.68 5.36 0.59 1.53 K=4
|
| 191 |
+
verify 14: accepted 0/3 (K=4) + correction -> +1 tokens (126.5 ms) cpos=61
|
| 192 |
+
[margins] 0.92 3.89 0.44 2.35 0.05 K=3
|
| 193 |
+
verify 15: accepted 1/2 (K=3) + correction -> +2 tokens (114.7 ms) cpos=63
|
| 194 |
+
[margins] 1.94 4.97 0.08 1.67 0.90 K=3
|
| 195 |
+
verify 16: accepted 0/2 (K=3) + correction -> +1 tokens (115.9 ms) cpos=64
|
| 196 |
+
[margins] 4.68 0.31 0.60 6.94 0.57 K=2
|
| 197 |
+
verify 17: accepted 1/1 (K=2) + correction -> +2 tokens (97.9 ms) cpos=66
|
| 198 |
+
[margins] 1.32 1.46 3.17 4.97 0.32 K=2
|
| 199 |
+
verify 18: accepted 1/1 (K=2) + correction -> +2 tokens (104.4 ms) cpos=68
|
| 200 |
+
[margins] 0.47 6.48 0.16 0.70 1.07 K=3
|
| 201 |
+
verify 19: accepted 2/2 (K=3) + correction -> +3 tokens (112.0 ms) cpos=71
|
| 202 |
+
[margins] 2.69 1.67 1.20 4.73 0.73 K=3
|
| 203 |
+
verify 20: accepted 2/2 (K=3) + correction -> +3 tokens (115.1 ms) cpos=74
|
| 204 |
+
[margins] 7.06 1.81 3.10 2.73 3.06 K=6
|
| 205 |
+
verify 21: accepted 5/5 (K=6) + correction -> +6 tokens (161.1 ms) cpos=80
|
| 206 |
+
[margins] 5.36 5.12 4.45 2.26 6.47 K=6
|
| 207 |
+
verify 22: accepted 5/5 (K=6) + correction -> +6 tokens (160.3 ms) cpos=86
|
| 208 |
+
[margins] 7.59 4.01 2.39 5.32 0.11 K=5
|
| 209 |
+
verify 23: accepted 4/4 (K=5) + correction -> +5 tokens (144.2 ms) cpos=91
|
| 210 |
+
[margins] 6.64 4.12 3.50 8.32 1.08 K=5
|
| 211 |
+
verify 24: accepted 4/4 (K=5) + correction -> +5 tokens (146.7 ms) cpos=96
|
| 212 |
+
[margins] 8.29 4.87 4.10 8.52 2.45 K=6
|
| 213 |
+
verify 25: accepted 5/5 (K=6) + correction -> +6 tokens (158.8 ms) cpos=102
|
| 214 |
+
[margins] 9.99 3.21 6.98 7.27 5.90 K=6
|
| 215 |
+
verify 26: accepted 5/5 (K=6) + correction -> +6 tokens (165.7 ms) cpos=108
|
| 216 |
+
[margins] 2.56 1.49 0.25 6.66 3.55 K=2
|
| 217 |
+
verify 27: accepted 0/1 (K=2) + correction -> +1 tokens (102.4 ms) cpos=109
|
| 218 |
+
[margins] 8.92 5.87 5.12 6.71 5.54 K=6
|
| 219 |
+
verify 28: accepted 5/5 (K=6) + correction -> +6 tokens (160.0 ms) cpos=115
|
| 220 |
+
[margins] 8.98 8.48 8.71 2.75 6.27 K=6
|
| 221 |
+
verify 29: accepted 5/5 (K=6) + correction -> +6 tokens (167.5 ms) cpos=121
|
| 222 |
+
[margins] 8.40 4.15 5.24 7.55 0.58 K=5
|
| 223 |
+
verify 30: accepted 4/4 (K=5) + correction -> +5 tokens (147.6 ms) cpos=126
|
| 224 |
+
[margins] 7.45 5.62 6.15 1.06 0.92 K=4
|
| 225 |
+
verify 31: accepted 3/3 (K=4) + correction -> +4 tokens (148.9 ms) cpos=130
|
| 226 |
+
[margins] 8.17 7.08 4.84 2.92 8.96 K=6
|
| 227 |
+
verify 32: accepted 5/5 (K=6) + correction -> +6 tokens (166.6 ms) cpos=136
|
| 228 |
+
[margins] 6.98 4.75 6.45 7.84 2.48 K=6
|
| 229 |
+
verify 33: accepted 5/5 (K=6) + correction -> +6 tokens (162.5 ms) cpos=142
|
| 230 |
+
[margins] 12.01 5.59 9.42 10.23 8.38 K=6
|
| 231 |
+
verify 34: accepted 5/5 (K=6) + correction -> +6 tokens (168.7 ms) cpos=148
|
| 232 |
+
[margins] 2.09 0.06 7.71 4.32 4.21 K=2
|
| 233 |
+
verify 35: accepted 0/1 (K=2) + correction -> +1 tokens (103.7 ms) cpos=149
|
| 234 |
+
[margins] 8.92 9.79 7.62 8.30 4.38 K=6
|
| 235 |
+
verify 36: accepted 5/5 (K=6) + correction -> +6 tokens (161.1 ms) cpos=155
|
| 236 |
+
[margins] 9.86 7.86 8.09 2.48 7.58 K=6
|
| 237 |
+
verify 37: accepted 5/5 (K=6) + correction -> +6 tokens (168.0 ms) cpos=161
|
| 238 |
+
[margins] 8.89 6.57 5.07 8.25 6.92 K=6
|
| 239 |
+
verify 38: accepted 5/5 (K=6) + correction -> +6 tokens (162.0 ms) cpos=167
|
| 240 |
+
[margins] 13.32 5.42 10.41 9.78 10.07 K=6
|
| 241 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (168.6 ms) cpos=173
|
| 242 |
+
[margins] 2.97 6.92 9.69 6.66 6.12 K=6
|
| 243 |
+
verify 40: accepted 5/5 (K=6) + correction -> +6 tokens (160.6 ms) cpos=179
|
| 244 |
+
[margins] 10.23 10.13 6.61 8.05 5.89 K=6
|
| 245 |
+
verify 41: accepted 5/5 (K=6) + correction -> +6 tokens (165.8 ms) cpos=185
|
| 246 |
+
[margins] 10.29 9.82 9.46 7.67 8.46 K=6
|
| 247 |
+
verify 42: accepted 5/5 (K=6) + correction -> +6 tokens (161.8 ms) cpos=191
|
| 248 |
+
[margins] 11.29 8.92 5.59 8.81 0.86 K=5
|
| 249 |
+
verify 43: accepted 4/4 (K=5) + correction -> +5 tokens (152.2 ms) cpos=196
|
| 250 |
+
[margins] 11.22 6.95 9.87 9.22 5.71 K=6
|
| 251 |
+
verify 44: accepted 5/5 (K=6) + correction -> +6 tokens (163.2 ms) cpos=202
|
| 252 |
+
[margins] 13.47 6.09 8.01 6.30 6.39 K=6
|
| 253 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (169.1 ms) cpos=208
|
| 254 |
+
[margins] 3.58 1.04 0.21 0.73 0.35 K=2
|
| 255 |
+
verify 46: accepted 0/1 (K=2) + correction -> +1 tokens (104.2 ms) cpos=209
|
| 256 |
+
[margins] 8.19 6.21 6.88 8.44 8.08 K=6
|
| 257 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (162.7 ms) cpos=215
|
| 258 |
+
[margins] 8.26 11.85 8.64 8.71 8.11 K=6
|
| 259 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (169.9 ms) cpos=221
|
| 260 |
+
[margins] 9.15 3.50 9.40 9.32 0.85 K=5
|
| 261 |
+
verify 49: accepted 4/4 (K=5) + correction -> +5 tokens (148.9 ms) cpos=226
|
| 262 |
+
[margins] 12.10 4.67 6.82 6.47 5.41 K=6
|
| 263 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (168.6 ms) cpos=232
|
| 264 |
+
[margins] 12.88 5.61 10.76 8.86 8.30 K=6
|
| 265 |
+
verify 51: accepted 5/5 (K=6) + correction -> +6 tokens (165.5 ms) cpos=238
|
| 266 |
+
|
| 267 |
+
[spec] generated 204 tokens over 51 verifies: mean tokens/verify = 4.00 (block=5, max 6)
|
| 268 |
+
[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
|
| 269 |
+
[spec] SPEC-DECODE: 34.2 ms/tok = 29.25 tok/s (vs base M=1 71.5 ms/tok = 13.99 tok/s -> 2.09x)
|
| 270 |
+
[decode] PREFILL: 41 positions in 700.1 ms = 58.6 tok/s (17.074 ms/tok)
|
| 271 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=2 s=42)...
|
| 272 |
+
[margins] 7.63 0.52 0.05 1.04 2.60 K=2
|
| 273 |
+
verify 1: accepted 1/1 (K=2) + correction -> +2 tokens (100.3 ms) cpos=43
|
| 274 |
+
[margins] 0.94 3.85 1.60 1.39 0.76 K=4
|
| 275 |
+
verify 2: accepted 3/3 (K=4) + correction -> +4 tokens (115.0 ms) cpos=47
|
| 276 |
+
[margins] 0.04 7.27 0.83 0.01 0.52 K=3
|
| 277 |
+
verify 3: accepted 0/2 (K=3) + correction -> +1 tokens (109.6 ms) cpos=48
|
| 278 |
+
[margins] 3.93 5.88 0.22 0.46 1.38 K=3
|
| 279 |
+
verify 4: accepted 0/2 (K=3) + correction -> +1 tokens (109.5 ms) cpos=49
|
| 280 |
+
[margins] 3.34 8.00 0.04 0.29 0.19 K=3
|
| 281 |
+
verify 5: accepted 0/2 (K=3) + correction -> +1 tokens (114.7 ms) cpos=50
|
| 282 |
+
[margins] 1.99 4.83 2.74 0.50 0.89 K=4
|
| 283 |
+
verify 6: accepted 0/3 (K=4) + correction -> +1 tokens (115.0 ms) cpos=51
|
| 284 |
+
[margins] 7.10 4.78 1.16 0.14 0.65 K=3
|
| 285 |
+
verify 7: accepted 1/2 (K=3) + correction -> +2 tokens (110.4 ms) cpos=53
|
| 286 |
+
[margins] 0.61 2.78 6.75 1.36 0.45 K=4
|
| 287 |
+
verify 8: accepted 0/3 (K=4) + correction -> +1 tokens (126.8 ms) cpos=54
|
| 288 |
+
[margins] 2.22 7.66 2.58 1.83 0.46 K=5
|
| 289 |
+
verify 9: accepted 2/4 (K=5) + correction -> +3 tokens (133.2 ms) cpos=57
|
| 290 |
+
[margins] 0.59 2.33 9.00 0.47 0.09 K=4
|
| 291 |
+
verify 10: accepted 0/3 (K=4) + correction -> +1 tokens (126.8 ms) cpos=58
|
| 292 |
+
[margins] 4.30 5.35 2.99 5.67 0.03 K=5
|
| 293 |
+
verify 11: accepted 2/4 (K=5) + correction -> +3 tokens (133.9 ms) cpos=61
|
| 294 |
+
[margins] 4.39 3.48 7.82 2.79 6.80 K=6
|
| 295 |
+
verify 12: accepted 3/5 (K=6) + correction -> +4 tokens (153.2 ms) cpos=65
|
| 296 |
+
[margins] 2.03 2.56 5.44 2.58 7.31 K=6
|
| 297 |
+
verify 13: accepted 3/5 (K=6) + correction -> +4 tokens (152.6 ms) cpos=69
|
| 298 |
+
[margins] 5.39 5.48 4.44 0.55 4.38 K=4
|
| 299 |
+
verify 14: accepted 2/3 (K=4) + correction -> +3 tokens (129.4 ms) cpos=72
|
| 300 |
+
[margins] 5.65 0.38 0.94 3.60 1.82 K=2
|
| 301 |
+
verify 15: accepted 1/1 (K=2) + correction -> +2 tokens (97.8 ms) cpos=74
|
| 302 |
+
[margins] 3.57 5.26 2.81 0.19 4.74 K=4
|
| 303 |
+
verify 16: accepted 1/3 (K=4) + correction -> +2 tokens (126.3 ms) cpos=76
|
| 304 |
+
[margins] 9.91 4.64 5.23 4.47 0.08 K=5
|
| 305 |
+
verify 17: accepted 2/4 (K=5) + correction -> +3 tokens (140.5 ms) cpos=79
|
| 306 |
+
[margins] 15.17 10.36 6.06 4.71 0.15 K=5
|
| 307 |
+
verify 18: accepted 4/4 (K=5) + correction -> +5 tokens (145.6 ms) cpos=84
|
| 308 |
+
[margins] 18.66 8.90 2.63 0.52 1.52 K=4
|
| 309 |
+
verify 19: accepted 2/3 (K=4) + correction -> +3 tokens (130.5 ms) cpos=87
|
| 310 |
+
[margins] 11.69 14.22 13.29 2.52 9.96 K=6
|
| 311 |
+
verify 20: accepted 5/5 (K=6) + correction -> +6 tokens (161.9 ms) cpos=93
|
| 312 |
+
[margins] 9.08 9.86 11.82 8.41 2.16 K=6
|
| 313 |
+
verify 21: accepted 4/5 (K=6) + correction -> +5 tokens (157.2 ms) cpos=98
|
| 314 |
+
[margins] 9.33 6.98 5.51 3.39 0.55 K=5
|
| 315 |
+
verify 22: accepted 4/4 (K=5) + correction -> +5 tokens (141.1 ms) cpos=103
|
| 316 |
+
[margins] 15.71 13.14 10.74 2.43 2.50 K=6
|
| 317 |
+
verify 23: accepted 5/5 (K=6) + correction -> +6 tokens (164.6 ms) cpos=109
|
| 318 |
+
[margins] 10.64 2.88 5.11 7.86 4.22 K=6
|
| 319 |
+
verify 24: accepted 5/5 (K=6) + correction -> +6 tokens (154.7 ms) cpos=115
|
| 320 |
+
[margins] 10.91 9.05 10.73 0.49 2.78 K=4
|
| 321 |
+
verify 25: accepted 3/3 (K=4) + correction -> +4 tokens (130.9 ms) cpos=119
|
| 322 |
+
[margins] 4.35 7.66 0.18 3.26 1.24 K=3
|
| 323 |
+
verify 26: accepted 2/2 (K=3) + correction -> +3 tokens (116.7 ms) cpos=122
|
| 324 |
+
[margins] 14.70 4.43 2.79 9.44 0.99 K=5
|
| 325 |
+
verify 27: accepted 4/4 (K=5) + correction -> +5 tokens (143.7 ms) cpos=127
|
| 326 |
+
[margins] 17.83 11.05 9.43 8.30 9.28 K=6
|
| 327 |
+
verify 28: accepted 5/5 (K=6) + correction -> +6 tokens (181.9 ms) cpos=133
|
| 328 |
+
[margins] 8.59 6.01 3.38 2.32 0.13 K=5
|
| 329 |
+
verify 29: accepted 4/4 (K=5) + correction -> +5 tokens (142.2 ms) cpos=138
|
| 330 |
+
[margins] 15.82 11.90 11.61 5.37 0.48 K=5
|
| 331 |
+
verify 30: accepted 4/4 (K=5) + correction -> +5 tokens (143.7 ms) cpos=143
|
| 332 |
+
[margins] 16.19 9.83 5.73 3.33 2.50 K=6
|
| 333 |
+
verify 31: accepted 5/5 (K=6) + correction -> +6 tokens (166.3 ms) cpos=149
|
| 334 |
+
[margins] 13.36 6.37 6.06 0.48 1.07 K=4
|
| 335 |
+
verify 32: accepted 3/3 (K=4) + correction -> +4 tokens (133.2 ms) cpos=153
|
| 336 |
+
[margins] 1.77 8.37 12.09 5.87 5.35 K=6
|
| 337 |
+
verify 33: accepted 4/5 (K=6) + correction -> +5 tokens (161.2 ms) cpos=158
|
| 338 |
+
[margins] 11.71 6.01 8.84 0.26 0.14 K=4
|
| 339 |
+
verify 34: accepted 3/3 (K=4) + correction -> +4 tokens (129.9 ms) cpos=162
|
| 340 |
+
[margins] 14.07 0.50 2.52 4.30 2.38 K=2
|
| 341 |
+
verify 35: accepted 1/1 (K=2) + correction -> +2 tokens (103.9 ms) cpos=164
|
| 342 |
+
[margins] 11.92 8.27 1.67 1.43 0.27 K=4
|
| 343 |
+
verify 36: accepted 2/3 (K=4) + correction -> +3 tokens (132.3 ms) cpos=167
|
| 344 |
+
[margins] 6.88 12.56 10.51 6.56 2.40 K=6
|
| 345 |
+
verify 37: accepted 4/5 (K=6) + correction -> +5 tokens (165.7 ms) cpos=172
|
| 346 |
+
[margins] 15.01 6.26 10.90 6.92 1.10 K=5
|
| 347 |
+
verify 38: accepted 4/4 (K=5) + correction -> +5 tokens (145.0 ms) cpos=177
|
| 348 |
+
[margins] 14.06 14.79 12.82 9.07 3.73 K=6
|
| 349 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (160.9 ms) cpos=183
|
| 350 |
+
[margins] 13.52 9.32 8.85 0.23 5.70 K=4
|
| 351 |
+
verify 40: accepted 3/3 (K=4) + correction -> +4 tokens (133.0 ms) cpos=187
|
| 352 |
+
[margins] 9.98 12.12 9.52 5.36 0.18 K=5
|
| 353 |
+
verify 41: accepted 4/4 (K=5) + correction -> +5 tokens (153.0 ms) cpos=192
|
| 354 |
+
[margins] 12.44 6.62 3.37 6.49 0.89 K=5
|
| 355 |
+
verify 42: accepted 4/4 (K=5) + correction -> +5 tokens (146.7 ms) cpos=197
|
| 356 |
+
[margins] 16.41 12.71 1.04 6.22 3.33 K=3
|
| 357 |
+
verify 43: accepted 2/2 (K=3) + correction -> +3 tokens (121.8 ms) cpos=200
|
| 358 |
+
[margins] 14.67 10.67 11.10 5.62 6.81 K=6
|
| 359 |
+
verify 44: accepted 5/5 (K=6) + correction -> +6 tokens (163.6 ms) cpos=206
|
| 360 |
+
[margins] 3.76 14.05 0.74 3.92 2.47 K=3
|
| 361 |
+
verify 45: accepted 2/2 (K=3) + correction -> +3 tokens (118.7 ms) cpos=209
|
| 362 |
+
[margins] 15.82 3.46 12.17 6.55 4.42 K=6
|
| 363 |
+
verify 46: accepted 3/5 (K=6) + correction -> +4 tokens (157.3 ms) cpos=213
|
| 364 |
+
[margins] 20.32 11.75 6.56 12.19 2.57 K=6
|
| 365 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (160.2 ms) cpos=219
|
| 366 |
+
[margins] 20.76 9.90 20.83 5.92 13.90 K=6
|
| 367 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (170.2 ms) cpos=225
|
| 368 |
+
[margins] 7.58 24.62 6.60 14.43 10.47 K=6
|
| 369 |
+
verify 49: accepted 5/5 (K=6) + correction -> +6 tokens (163.3 ms) cpos=231
|
| 370 |
+
[margins] 27.65 11.21 14.92 2.21 6.42 K=6
|
| 371 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (169.6 ms) cpos=237
|
| 372 |
+
[margins] 12.75 11.89 5.14 1.96 6.77 K=6
|
| 373 |
+
verify 51: accepted 5/5 (K=6) + correction -> +6 tokens (164.2 ms) cpos=243
|
| 374 |
+
|
| 375 |
+
[spec] generated 202 tokens over 51 verifies: mean tokens/verify = 3.96 (block=5, max 6)
|
| 376 |
+
[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
|
| 377 |
+
[spec] SPEC-DECODE: 35.1 ms/tok = 28.45 tok/s (vs base M=1 71.5 ms/tok = 13.99 tok/s -> 2.03x)
|
| 378 |
+
[decode] PREFILL: 26 positions in 453.8 ms = 57.3 tok/s (17.455 ms/tok)
|
| 379 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=3 s=27)...
|
| 380 |
+
[margins] 1.79 2.75 1.49 0.66 0.50 K=3
|
| 381 |
+
verify 1: accepted 1/2 (K=3) + correction -> +2 tokens (114.9 ms) cpos=28
|
| 382 |
+
[margins] 3.74 1.23 0.13 0.66 2.13 K=2
|
| 383 |
+
verify 2: accepted 1/1 (K=2) + correction -> +2 tokens (99.3 ms) cpos=30
|
| 384 |
+
[margins] 3.62 1.83 0.08 0.07 2.93 K=3
|
| 385 |
+
verify 3: accepted 1/2 (K=3) + correction -> +2 tokens (109.3 ms) cpos=32
|
| 386 |
+
[margins] 3.17 3.22 2.26 0.88 0.74 K=4
|
| 387 |
+
verify 4: accepted 3/3 (K=4) + correction -> +4 tokens (118.3 ms) cpos=36
|
| 388 |
+
[margins] 3.79 5.76 2.68 1.46 1.96 K=4
|
| 389 |
+
verify 5: accepted 3/3 (K=4) + correction -> +4 tokens (118.5 ms) cpos=40
|
| 390 |
+
[margins] 3.22 7.73 2.69 3.79 3.04 K=6
|
| 391 |
+
verify 6: accepted 5/5 (K=6) + correction -> +6 tokens (143.4 ms) cpos=46
|
| 392 |
+
[margins] 2.65 9.55 3.42 6.34 3.56 K=6
|
| 393 |
+
verify 7: accepted 5/5 (K=6) + correction -> +6 tokens (149.8 ms) cpos=52
|
| 394 |
+
[margins] 0.98 9.53 3.01 7.38 4.31 K=6
|
| 395 |
+
verify 8: accepted 5/5 (K=6) + correction -> +6 tokens (145.0 ms) cpos=58
|
| 396 |
+
[margins] 1.00 8.86 2.51 6.99 3.98 K=6
|
| 397 |
+
verify 9: accepted 5/5 (K=6) + correction -> +6 tokens (151.0 ms) cpos=64
|
| 398 |
+
[margins] 2.13 8.05 3.42 6.61 4.97 K=6
|
| 399 |
+
verify 10: accepted 5/5 (K=6) + correction -> +6 tokens (144.6 ms) cpos=70
|
| 400 |
+
[margins] 1.22 8.63 2.62 6.97 4.58 K=6
|
| 401 |
+
verify 11: accepted 4/5 (K=6) + correction -> +5 tokens (151.6 ms) cpos=75
|
| 402 |
+
[margins] 7.82 2.72 5.71 2.65 3.82 K=6
|
| 403 |
+
verify 12: accepted 0/5 (K=6) + correction -> +1 tokens (155.7 ms) cpos=76
|
| 404 |
+
[margins] 2.37 6.39 0.37 1.88 0.05 K=3
|
| 405 |
+
verify 13: accepted 0/2 (K=3) + correction -> +1 tokens (110.4 ms) cpos=77
|
| 406 |
+
[margins] 1.66 3.84 0.22 1.02 0.39 K=3
|
| 407 |
+
verify 14: accepted 2/2 (K=3) + correction -> +3 tokens (114.0 ms) cpos=80
|
| 408 |
+
[margins] 1.28 2.18 1.73 3.62 1.13 K=5
|
| 409 |
+
verify 15: accepted 0/4 (K=5) + correction -> +1 tokens (136.9 ms) cpos=81
|
| 410 |
+
[margins] 1.55 0.44 0.32 0.47 0.97 K=2
|
| 411 |
+
verify 16: accepted 1/1 (K=2) + correction -> +2 tokens (97.9 ms) cpos=83
|
| 412 |
+
[margins] 0.96 0.39 0.12 0.40 0.03 K=2
|
| 413 |
+
verify 17: accepted 1/1 (K=2) + correction -> +2 tokens (101.3 ms) cpos=85
|
| 414 |
+
[margins] 4.39 1.53 0.24 0.56 1.45 K=3
|
| 415 |
+
verify 18: accepted 1/2 (K=3) + correction -> +2 tokens (112.7 ms) cpos=87
|
| 416 |
+
[margins] 3.13 2.36 1.07 2.49 0.41 K=3
|
| 417 |
+
verify 19: accepted 1/2 (K=3) + correction -> +2 tokens (115.2 ms) cpos=89
|
| 418 |
+
[margins] 1.62 1.85 0.36 0.77 0.63 K=3
|
| 419 |
+
verify 20: accepted 2/2 (K=3) + correction -> +3 tokens (113.7 ms) cpos=92
|
| 420 |
+
[margins] 3.10 0.76 0.25 1.72 3.15 K=2
|
| 421 |
+
verify 21: accepted 1/1 (K=2) + correction -> +2 tokens (99.0 ms) cpos=94
|
| 422 |
+
[margins] 0.21 8.48 0.83 1.32 2.56 K=3
|
| 423 |
+
verify 22: accepted 2/2 (K=3) + correction -> +3 tokens (112.7 ms) cpos=97
|
| 424 |
+
[margins] 2.90 2.35 0.20 0.83 0.38 K=3
|
| 425 |
+
verify 23: accepted 2/2 (K=3) + correction -> +3 tokens (117.2 ms) cpos=100
|
| 426 |
+
[margins] 0.01 0.95 3.14 0.13 0.51 K=2
|
| 427 |
+
verify 24: accepted 1/1 (K=2) + correction -> +2 tokens (97.5 ms) cpos=102
|
| 428 |
+
[margins] 1.38 0.36 0.44 3.15 7.98 K=2
|
| 429 |
+
verify 25: accepted 0/1 (K=2) + correction -> +1 tokens (102.4 ms) cpos=103
|
| 430 |
+
[margins] 5.69 6.77 0.90 3.98 6.55 K=3
|
| 431 |
+
verify 26: accepted 2/2 (K=3) + correction -> +3 tokens (112.7 ms) cpos=106
|
| 432 |
+
[margins] 6.52 5.25 0.31 4.93 1.52 K=3
|
| 433 |
+
verify 27: accepted 2/2 (K=3) + correction -> +3 tokens (113.3 ms) cpos=109
|
| 434 |
+
[margins] 8.83 1.54 1.46 1.41 0.81 K=3
|
| 435 |
+
verify 28: accepted 2/2 (K=3) + correction -> +3 tokens (117.3 ms) cpos=112
|
| 436 |
+
[margins] 9.79 0.08 2.14 0.93 0.31 K=2
|
| 437 |
+
verify 29: accepted 1/1 (K=2) + correction -> +2 tokens (103.5 ms) cpos=114
|
| 438 |
+
[margins] 0.59 9.04 1.74 1.69 2.27 K=6
|
| 439 |
+
verify 30: accepted 2/5 (K=6) + correction -> +3 tokens (161.0 ms) cpos=117
|
| 440 |
+
[margins] 0.76 5.37 3.75 3.18 7.97 K=6
|
| 441 |
+
verify 31: accepted 5/5 (K=6) + correction -> +6 tokens (161.4 ms) cpos=123
|
| 442 |
+
[margins] 9.57 10.96 3.62 11.97 4.36 K=6
|
| 443 |
+
verify 32: accepted 5/5 (K=6) + correction -> +6 tokens (177.8 ms) cpos=129
|
| 444 |
+
[margins] 10.62 10.95 11.11 6.57 4.14 K=6
|
| 445 |
+
verify 33: accepted 5/5 (K=6) + correction -> +6 tokens (159.9 ms) cpos=135
|
| 446 |
+
[margins] 3.79 1.24 0.93 2.04 0.55 K=2
|
| 447 |
+
verify 34: accepted 1/1 (K=2) + correction -> +2 tokens (107.1 ms) cpos=137
|
| 448 |
+
[margins] 1.21 0.10 0.49 7.82 1.59 K=2
|
| 449 |
+
verify 35: accepted 0/1 (K=2) + correction -> +1 tokens (101.7 ms) cpos=138
|
| 450 |
+
[margins] 0.78 2.01 1.04 1.17 0.43 K=3
|
| 451 |
+
verify 36: accepted 1/2 (K=3) + correction -> +2 tokens (115.4 ms) cpos=140
|
| 452 |
+
[margins] 3.13 1.68 0.79 0.05 0.52 K=3
|
| 453 |
+
verify 37: accepted 0/2 (K=3) + correction -> +1 tokens (112.9 ms) cpos=141
|
| 454 |
+
[margins] 1.78 0.20 0.73 0.19 2.75 K=2
|
| 455 |
+
verify 38: accepted 1/1 (K=2) + correction -> +2 tokens (99.5 ms) cpos=143
|
| 456 |
+
[margins] 0.81 0.24 0.06 0.47 0.74 K=2
|
| 457 |
+
verify 39: accepted 0/1 (K=2) + correction -> +1 tokens (105.5 ms) cpos=144
|
| 458 |
+
[margins] 1.49 3.29 1.73 2.33 0.38 K=5
|
| 459 |
+
verify 40: accepted 1/4 (K=5) + correction -> +2 tokens (141.2 ms) cpos=146
|
| 460 |
+
[margins] 7.74 1.67 1.64 1.61 0.30 K=5
|
| 461 |
+
verify 41: accepted 2/4 (K=5) + correction -> +3 tokens (140.2 ms) cpos=149
|
| 462 |
+
[margins] 1.56 2.00 3.04 0.62 1.31 K=4
|
| 463 |
+
verify 42: accepted 0/3 (K=4) + correction -> +1 tokens (128.7 ms) cpos=150
|
| 464 |
+
[margins] 1.75 0.74 0.36 1.87 0.39 K=2
|
| 465 |
+
verify 43: accepted 1/1 (K=2) + correction -> +2 tokens (102.1 ms) cpos=152
|
| 466 |
+
[margins] 3.88 0.45 1.40 1.13 1.00 K=2
|
| 467 |
+
verify 44: accepted 1/1 (K=2) + correction -> +2 tokens (99.5 ms) cpos=154
|
| 468 |
+
[margins] 0.73 1.19 3.43 0.24 0.44 K=2
|
| 469 |
+
verify 45: accepted 1/1 (K=2) + correction -> +2 tokens (105.1 ms) cpos=156
|
| 470 |
+
[margins] 5.10 2.09 0.69 1.20 0.55 K=3
|
| 471 |
+
verify 46: accepted 1/2 (K=3) + correction -> +2 tokens (110.9 ms) cpos=158
|
| 472 |
+
[margins] 2.59 1.76 1.65 0.11 1.24 K=4
|
| 473 |
+
verify 47: accepted 3/3 (K=4) + correction -> +4 tokens (131.6 ms) cpos=162
|
| 474 |
+
[margins] 5.79 3.09 0.21 1.07 0.42 K=3
|
| 475 |
+
verify 48: accepted 2/2 (K=3) + correction -> +3 tokens (114.7 ms) cpos=165
|
| 476 |
+
[margins] 3.42 1.65 1.39 1.53 1.60 K=3
|
| 477 |
+
verify 49: accepted 2/2 (K=3) + correction -> +3 tokens (113.9 ms) cpos=168
|
| 478 |
+
[margins] 4.78 1.84 7.44 3.02 1.28 K=5
|
| 479 |
+
verify 50: accepted 4/4 (K=5) + correction -> +5 tokens (143.9 ms) cpos=173
|
| 480 |
+
[margins] 0.27 0.11 1.50 0.41 0.42 K=2
|
| 481 |
+
verify 51: accepted 0/1 (K=2) + correction -> +1 tokens (102.0 ms) cpos=174
|
| 482 |
+
[margins] 0.08 2.10 0.60 3.90 2.81 K=3
|
| 483 |
+
verify 52: accepted 0/2 (K=3) + correction -> +1 tokens (118.7 ms) cpos=175
|
| 484 |
+
[margins] 0.32 1.19 0.85 0.25 1.94 K=2
|
| 485 |
+
verify 53: accepted 1/1 (K=2) + correction -> +2 tokens (106.9 ms) cpos=177
|
| 486 |
+
[margins] 6.45 1.88 1.49 1.86 2.29 K=3
|
| 487 |
+
verify 54: accepted 2/2 (K=3) + correction -> +3 tokens (116.5 ms) cpos=180
|
| 488 |
+
[margins] 0.49 2.15 2.02 0.62 0.10 K=4
|
| 489 |
+
verify 55: accepted 0/3 (K=4) + correction -> +1 tokens (129.4 ms) cpos=181
|
| 490 |
+
[margins] 5.35 0.98 0.87 1.81 1.48 K=2
|
| 491 |
+
verify 56: accepted 1/1 (K=2) + correction -> +2 tokens (100.0 ms) cpos=183
|
| 492 |
+
[margins] 3.24 2.84 5.55 2.43 2.63 K=6
|
| 493 |
+
verify 57: accepted 2/5 (K=6) + correction -> +3 tokens (160.4 ms) cpos=186
|
| 494 |
+
[margins] 2.61 2.32 0.08 0.08 0.84 K=3
|
| 495 |
+
verify 58: accepted 2/2 (K=3) + correction -> +3 tokens (118.1 ms) cpos=189
|
| 496 |
+
[margins] 3.13 1.70 0.20 0.16 0.54 K=3
|
| 497 |
+
verify 59: accepted 2/2 (K=3) + correction -> +3 tokens (119.7 ms) cpos=192
|
| 498 |
+
[margins] 7.13 0.32 0.19 1.06 1.00 K=2
|
| 499 |
+
verify 60: accepted 1/1 (K=2) + correction -> +2 tokens (100.1 ms) cpos=194
|
| 500 |
+
[margins] 0.22 1.63 3.16 0.96 0.44 K=4
|
| 501 |
+
verify 61: accepted 0/3 (K=4) + correction -> +1 tokens (131.4 ms) cpos=195
|
| 502 |
+
[margins] 1.84 0.77 2.14 3.54 0.30 K=2
|
| 503 |
+
verify 62: accepted 1/1 (K=2) + correction -> +2 tokens (104.0 ms) cpos=197
|
| 504 |
+
[margins] 0.68 0.89 6.72 0.79 2.59 K=2
|
| 505 |
+
verify 63: accepted 0/1 (K=2) + correction -> +1 tokens (100.0 ms) cpos=198
|
| 506 |
+
[margins] 2.04 0.56 1.17 4.66 0.22 K=2
|
| 507 |
+
verify 64: accepted 0/1 (K=2) + correction -> +1 tokens (106.0 ms) cpos=199
|
| 508 |
+
[margins] 4.37 6.44 6.80 0.89 4.84 K=4
|
| 509 |
+
verify 65: accepted 0/3 (K=4) + correction -> +1 tokens (131.0 ms) cpos=200
|
| 510 |
+
[margins] 7.29 3.89 0.09 2.84 2.98 K=3
|
| 511 |
+
verify 66: accepted 2/2 (K=3) + correction -> +3 tokens (113.2 ms) cpos=203
|
| 512 |
+
[margins] 4.21 3.76 2.14 2.26 1.14 K=5
|
| 513 |
+
verify 67: accepted 1/4 (K=5) + correction -> +2 tokens (143.5 ms) cpos=205
|
| 514 |
+
[margins] 1.79 0.27 0.33 0.42 1.28 K=2
|
| 515 |
+
verify 68: accepted 1/1 (K=2) + correction -> +2 tokens (99.5 ms) cpos=207
|
| 516 |
+
[margins] 0.03 2.25 1.28 3.17 3.50 K=3
|
| 517 |
+
verify 69: accepted 0/2 (K=3) + correction -> +1 tokens (118.7 ms) cpos=208
|
| 518 |
+
[margins] 10.48 0.94 1.65 4.53 0.97 K=2
|
| 519 |
+
verify 70: accepted 1/1 (K=2) + correction -> +2 tokens (101.8 ms) cpos=210
|
| 520 |
+
[margins] 2.31 5.03 0.65 1.42 4.38 K=3
|
| 521 |
+
verify 71: accepted 2/2 (K=3) + correction -> +3 tokens (118.3 ms) cpos=213
|
| 522 |
+
[margins] 0.88 0.03 0.85 0.84 0.26 K=2
|
| 523 |
+
verify 72: accepted 1/1 (K=2) + correction -> +2 tokens (99.6 ms) cpos=215
|
| 524 |
+
[margins] 3.27 2.22 4.43 4.44 2.45 K=6
|
| 525 |
+
verify 73: accepted 4/5 (K=6) + correction -> +5 tokens (166.5 ms) cpos=220
|
| 526 |
+
[margins] 4.09 2.30 1.90 1.05 1.56 K=4
|
| 527 |
+
verify 74: accepted 0/3 (K=4) + correction -> +1 tokens (133.5 ms) cpos=221
|
| 528 |
+
[margins] 10.80 2.31 2.11 0.28 1.20 K=4
|
| 529 |
+
verify 75: accepted 3/3 (K=4) + correction -> +4 tokens (131.4 ms) cpos=225
|
| 530 |
+
[margins] 12.90 5.49 1.36 1.40 0.29 K=3
|
| 531 |
+
verify 76: accepted 2/2 (K=3) + correction -> +3 tokens (119.9 ms) cpos=228
|
| 532 |
+
|
| 533 |
+
[spec] generated 202 tokens over 76 verifies: mean tokens/verify = 2.66 (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: 45.4 ms/tok = 22.01 tok/s (vs base M=1 71.5 ms/tok = 13.99 tok/s -> 1.57x)
|
| 536 |
+
[decode] PREFILL: 14 positions in 281.3 ms = 49.8 tok/s (20.091 ms/tok)
|
| 537 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=4 s=15)...
|
| 538 |
+
[margins] 0.19 8.68 2.54 3.60 4.40 K=6
|
| 539 |
+
verify 1: accepted 0/5 (K=6) + correction -> +1 tokens (158.8 ms) cpos=15
|
| 540 |
+
[margins] 0.72 1.75 0.05 1.23 0.18 K=3
|
| 541 |
+
verify 2: accepted 1/2 (K=3) + correction -> +2 tokens (111.9 ms) cpos=17
|
| 542 |
+
[margins] 0.27 0.67 0.09 1.01 0.96 K=2
|
| 543 |
+
verify 3: accepted 0/1 (K=2) + correction -> +1 tokens (95.9 ms) cpos=18
|
| 544 |
+
[margins] 1.47 0.74 0.47 0.07 1.55 K=2
|
| 545 |
+
verify 4: accepted 1/1 (K=2) + correction -> +2 tokens (99.5 ms) cpos=20
|
| 546 |
+
[margins] 0.82 1.16 0.33 0.62 1.40 K=2
|
| 547 |
+
verify 5: accepted 1/1 (K=2) + correction -> +2 tokens (94.5 ms) cpos=22
|
| 548 |
+
[margins] 2.14 1.02 0.38 0.83 0.28 K=2
|
| 549 |
+
verify 6: accepted 1/1 (K=2) + correction -> +2 tokens (101.1 ms) cpos=24
|
| 550 |
+
[margins] 0.01 0.63 0.00 1.42 3.99 K=2
|
| 551 |
+
verify 7: accepted 1/1 (K=2) + correction -> +2 tokens (96.7 ms) cpos=26
|
| 552 |
+
[margins] 0.01 0.00 0.60 0.59 0.30 K=2
|
| 553 |
+
verify 8: accepted 0/1 (K=2) + correction -> +1 tokens (101.0 ms) cpos=27
|
| 554 |
+
[margins] 0.04 0.25 0.13 0.33 0.93 K=2
|
| 555 |
+
verify 9: accepted 1/1 (K=2) + correction -> +2 tokens (103.7 ms) cpos=29
|
| 556 |
+
[margins] 3.78 2.73 0.53 3.17 0.87 K=3
|
| 557 |
+
verify 10: accepted 2/2 (K=3) + correction -> +3 tokens (118.2 ms) cpos=32
|
| 558 |
+
[margins] 1.23 0.93 0.02 2.07 0.20 K=2
|
| 559 |
+
verify 11: accepted 1/1 (K=2) + correction -> +2 tokens (95.9 ms) cpos=34
|
| 560 |
+
[margins] 1.20 0.57 0.67 1.04 0.34 K=2
|
| 561 |
+
verify 12: accepted 1/1 (K=2) + correction -> +2 tokens (99.5 ms) cpos=36
|
| 562 |
+
[margins] 0.51 1.50 11.90 1.07 2.15 K=2
|
| 563 |
+
verify 13: accepted 0/1 (K=2) + correction -> +1 tokens (96.4 ms) cpos=37
|
| 564 |
+
[margins] 0.27 2.73 0.05 0.31 0.10 K=3
|
| 565 |
+
verify 14: accepted 1/2 (K=3) + correction -> +2 tokens (113.5 ms) cpos=39
|
| 566 |
+
[margins] 2.77 0.14 0.06 2.03 0.15 K=2
|
| 567 |
+
verify 15: accepted 0/1 (K=2) + correction -> +1 tokens (99.5 ms) cpos=40
|
| 568 |
+
[margins] 3.25 3.29 3.23 1.29 1.76 K=4
|
| 569 |
+
verify 16: accepted 1/3 (K=4) + correction -> +2 tokens (127.3 ms) cpos=42
|
| 570 |
+
[margins] 0.43 0.44 0.68 1.02 0.27 K=2
|
| 571 |
+
verify 17: accepted 1/1 (K=2) + correction -> +2 tokens (101.7 ms) cpos=44
|
| 572 |
+
[margins] 0.95 7.32 0.57 1.28 2.12 K=3
|
| 573 |
+
verify 18: accepted 2/2 (K=3) + correction -> +3 tokens (109.9 ms) cpos=47
|
| 574 |
+
[margins] 3.48 6.79 2.35 1.42 2.99 K=4
|
| 575 |
+
verify 19: accepted 3/3 (K=4) + correction -> +4 tokens (125.7 ms) cpos=51
|
| 576 |
+
[margins] 2.58 0.44 0.63 2.03 0.14 K=2
|
| 577 |
+
verify 20: accepted 0/1 (K=2) + correction -> +1 tokens (101.1 ms) cpos=52
|
| 578 |
+
[margins] 1.89 1.90 1.58 1.23 3.08 K=4
|
| 579 |
+
verify 21: accepted 0/3 (K=4) + correction -> +1 tokens (125.1 ms) cpos=53
|
| 580 |
+
[margins] 7.25 2.71 1.85 0.51 2.47 K=4
|
| 581 |
+
verify 22: accepted 2/3 (K=4) + correction -> +3 tokens (129.5 ms) cpos=56
|
| 582 |
+
[margins] 4.25 1.35 4.48 3.10 0.92 K=2
|
| 583 |
+
verify 23: accepted 1/1 (K=2) + correction -> +2 tokens (97.7 ms) cpos=58
|
| 584 |
+
[margins] 4.77 10.16 1.59 0.54 0.16 K=4
|
| 585 |
+
verify 24: accepted 2/3 (K=4) + correction -> +3 tokens (123.7 ms) cpos=61
|
| 586 |
+
[margins] 1.68 1.63 0.56 1.03 0.11 K=3
|
| 587 |
+
verify 25: accepted 0/2 (K=3) + correction -> +1 tokens (112.7 ms) cpos=62
|
| 588 |
+
[margins] 1.45 0.54 1.49 1.59 2.52 K=2
|
| 589 |
+
verify 26: accepted 0/1 (K=2) + correction -> +1 tokens (99.7 ms) cpos=63
|
| 590 |
+
[margins] 0.59 1.33 0.56 0.76 0.21 K=2
|
| 591 |
+
verify 27: accepted 1/1 (K=2) + correction -> +2 tokens (101.9 ms) cpos=65
|
| 592 |
+
[margins] 1.86 3.65 0.06 1.05 0.93 K=3
|
| 593 |
+
verify 28: accepted 0/2 (K=3) + correction -> +1 tokens (113.6 ms) cpos=66
|
| 594 |
+
[margins] 0.69 3.87 0.53 0.06 0.15 K=3
|
| 595 |
+
verify 29: accepted 0/2 (K=3) + correction -> +1 tokens (113.3 ms) cpos=67
|
| 596 |
+
[margins] 1.59 0.38 0.94 1.26 1.35 K=2
|
| 597 |
+
verify 30: accepted 1/1 (K=2) + correction -> +2 tokens (102.8 ms) cpos=69
|
| 598 |
+
[margins] 0.07 2.91 0.69 2.07 0.07 K=3
|
| 599 |
+
verify 31: accepted 0/2 (K=3) + correction -> +1 tokens (115.7 ms) cpos=70
|
| 600 |
+
[margins] 1.97 1.18 0.46 0.99 0.28 K=2
|
| 601 |
+
verify 32: accepted 0/1 (K=2) + correction -> +1 tokens (102.3 ms) cpos=71
|
| 602 |
+
[margins] 0.19 0.06 1.94 0.82 0.02 K=2
|
| 603 |
+
verify 33: accepted 0/1 (K=2) + correction -> +1 tokens (103.0 ms) cpos=72
|
| 604 |
+
[margins] 0.05 1.34 4.03 0.62 0.76 K=2
|
| 605 |
+
verify 34: accepted 0/1 (K=2) + correction -> +1 tokens (97.3 ms) cpos=73
|
| 606 |
+
[margins] 5.32 1.49 1.44 0.85 0.60 K=2
|
| 607 |
+
verify 35: accepted 1/1 (K=2) + correction -> +2 tokens (98.1 ms) cpos=75
|
| 608 |
+
[margins] 0.56 1.10 2.12 2.52 0.69 K=2
|
| 609 |
+
verify 36: accepted 1/1 (K=2) + correction -> +2 tokens (101.3 ms) cpos=77
|
| 610 |
+
[margins] 4.48 1.63 0.56 1.57 0.98 K=3
|
| 611 |
+
verify 37: accepted 2/2 (K=3) + correction -> +3 tokens (115.9 ms) cpos=80
|
| 612 |
+
[margins] 1.85 4.93 1.85 2.35 8.44 K=6
|
| 613 |
+
verify 38: accepted 5/5 (K=6) + correction -> +6 tokens (162.9 ms) cpos=86
|
| 614 |
+
[margins] 4.94 5.13 3.55 3.67 1.50 K=6
|
| 615 |
+
verify 39: accepted 2/5 (K=6) + correction -> +3 tokens (150.1 ms) cpos=89
|
| 616 |
+
[margins] 8.76 4.19 2.52 1.05 0.28 K=4
|
| 617 |
+
verify 40: accepted 1/3 (K=4) + correction -> +2 tokens (122.5 ms) cpos=91
|
| 618 |
+
[margins] 6.76 3.89 1.49 0.65 1.85 K=3
|
| 619 |
+
verify 41: accepted 1/2 (K=3) + correction -> +2 tokens (111.7 ms) cpos=93
|
| 620 |
+
[margins] 4.97 0.23 5.48 4.19 1.35 K=2
|
| 621 |
+
verify 42: accepted 1/1 (K=2) + correction -> +2 tokens (100.9 ms) cpos=95
|
| 622 |
+
[margins] 5.32 1.67 3.15 1.22 4.49 K=4
|
| 623 |
+
verify 43: accepted 3/3 (K=4) + correction -> +4 tokens (121.9 ms) cpos=99
|
| 624 |
+
[margins] 3.71 6.00 3.75 2.44 3.79 K=6
|
| 625 |
+
verify 44: accepted 5/5 (K=6) + correction -> +6 tokens (152.6 ms) cpos=105
|
| 626 |
+
[margins] 3.67 8.36 3.77 5.07 3.66 K=6
|
| 627 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (148.7 ms) cpos=111
|
| 628 |
+
[margins] 4.11 8.18 4.31 5.20 4.21 K=6
|
| 629 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (154.2 ms) cpos=117
|
| 630 |
+
[margins] 4.71 7.62 4.10 5.50 4.61 K=6
|
| 631 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (150.4 ms) cpos=123
|
| 632 |
+
[margins] 3.41 8.17 4.74 5.84 4.85 K=6
|
| 633 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (170.1 ms) cpos=129
|
| 634 |
+
[margins] 4.34 7.98 5.14 5.56 5.05 K=6
|
| 635 |
+
verify 49: accepted 5/5 (K=6) + correction -> +6 tokens (150.7 ms) cpos=135
|
| 636 |
+
[margins] 4.91 8.80 3.50 5.30 3.71 K=6
|
| 637 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (154.9 ms) cpos=141
|
| 638 |
+
[margins] 5.42 8.47 5.06 4.87 4.40 K=6
|
| 639 |
+
verify 51: accepted 5/5 (K=6) + correction -> +6 tokens (151.0 ms) cpos=147
|
| 640 |
+
[margins] 6.47 7.95 4.66 4.06 4.26 K=6
|
| 641 |
+
verify 52: accepted 5/5 (K=6) + correction -> +6 tokens (157.6 ms) cpos=153
|
| 642 |
+
[margins] 4.65 8.77 3.36 5.98 4.05 K=6
|
| 643 |
+
verify 53: accepted 2/5 (K=6) + correction -> +3 tokens (150.2 ms) cpos=156
|
| 644 |
+
[margins] 4.31 3.83 5.85 2.81 1.17 K=5
|
| 645 |
+
verify 54: accepted 1/4 (K=5) + correction -> +2 tokens (138.8 ms) cpos=158
|
| 646 |
+
[margins] 3.84 0.41 1.87 0.13 6.51 K=2
|
| 647 |
+
verify 55: accepted 0/1 (K=2) + correction -> +1 tokens (104.1 ms) cpos=159
|
| 648 |
+
[margins] 7.31 0.45 1.96 1.51 0.18 K=2
|
| 649 |
+
verify 56: accepted 1/1 (K=2) + correction -> +2 tokens (104.4 ms) cpos=161
|
| 650 |
+
[margins] 7.40 4.33 1.00 3.91 1.41 K=3
|
| 651 |
+
verify 57: accepted 2/2 (K=3) + correction -> +3 tokens (116.3 ms) cpos=164
|
| 652 |
+
[margins] 6.18 4.67 2.61 3.69 2.28 K=6
|
| 653 |
+
verify 58: accepted 2/5 (K=6) + correction -> +3 tokens (156.8 ms) cpos=167
|
| 654 |
+
[margins] 9.39 4.18 7.67 6.68 4.20 K=6
|
| 655 |
+
verify 59: accepted 5/5 (K=6) + correction -> +6 tokens (165.7 ms) cpos=173
|
| 656 |
+
[margins] 5.01 1.84 1.33 2.34 0.46 K=3
|
| 657 |
+
verify 60: accepted 1/2 (K=3) + correction -> +2 tokens (118.9 ms) cpos=175
|
| 658 |
+
[margins] 6.92 8.15 1.93 0.16 4.62 K=4
|
| 659 |
+
verify 61: accepted 3/3 (K=4) + correction -> +4 tokens (132.4 ms) cpos=179
|
| 660 |
+
[margins] 9.61 9.55 7.38 9.65 0.27 K=5
|
| 661 |
+
verify 62: accepted 4/4 (K=5) + correction -> +5 tokens (149.3 ms) cpos=184
|
| 662 |
+
[margins] 6.28 6.89 10.03 11.90 5.12 K=6
|
| 663 |
+
verify 63: accepted 5/5 (K=6) + correction -> +6 tokens (162.3 ms) cpos=190
|
| 664 |
+
[margins] 10.17 5.67 8.71 6.43 9.56 K=6
|
| 665 |
+
verify 64: accepted 5/5 (K=6) + correction -> +6 tokens (169.4 ms) cpos=196
|
| 666 |
+
[margins] 12.06 7.83 7.20 7.93 0.95 K=5
|
| 667 |
+
verify 65: accepted 4/4 (K=5) + correction -> +5 tokens (147.1 ms) cpos=201
|
| 668 |
+
[margins] 6.28 8.69 9.74 14.95 7.73 K=6
|
| 669 |
+
verify 66: accepted 5/5 (K=6) + correction -> +6 tokens (162.7 ms) cpos=207
|
| 670 |
+
[margins] 10.33 6.07 8.98 9.53 9.79 K=6
|
| 671 |
+
verify 67: accepted 5/5 (K=6) + correction -> +6 tokens (167.3 ms) cpos=213
|
| 672 |
+
[margins] 11.45 14.09 11.74 7.94 5.63 K=6
|
| 673 |
+
verify 68: accepted 4/5 (K=6) + correction -> +5 tokens (164.1 ms) cpos=218
|
| 674 |
+
|
| 675 |
+
[spec] generated 204 tokens over 68 verifies: mean tokens/verify = 3.00 (block=5, max 6)
|
| 676 |
+
[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
|
| 677 |
+
[spec] SPEC-DECODE: 41.0 ms/tok = 24.41 tok/s (vs base M=1 71.5 ms/tok = 13.99 tok/s -> 1.75x)
|
| 678 |
+
[decode] PREFILL: 82 positions in 1338.2 ms = 61.3 tok/s (16.320 ms/tok)
|
| 679 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=5 s=83)...
|
| 680 |
+
[margins] 8.06 3.64 1.20 0.79 2.93 K=3
|
| 681 |
+
verify 1: accepted 1/2 (K=3) + correction -> +2 tokens (118.6 ms) cpos=84
|
| 682 |
+
[margins] 0.04 0.53 0.14 0.12 0.84 K=2
|
| 683 |
+
verify 2: accepted 0/1 (K=2) + correction -> +1 tokens (101.3 ms) cpos=85
|
| 684 |
+
[margins] 0.03 0.34 0.66 1.29 0.46 K=2
|
| 685 |
+
verify 3: accepted 0/1 (K=2) + correction -> +1 tokens (97.1 ms) cpos=86
|
| 686 |
+
[margins] 4.70 4.46 0.23 0.29 1.48 K=3
|
| 687 |
+
verify 4: accepted 2/2 (K=3) + correction -> +3 tokens (115.3 ms) cpos=89
|
| 688 |
+
[margins] 4.70 5.48 2.47 1.64 4.18 K=6
|
| 689 |
+
verify 5: accepted 5/5 (K=6) + correction -> +6 tokens (156.3 ms) cpos=95
|
| 690 |
+
[margins] 6.94 1.78 3.47 6.15 1.81 K=6
|
| 691 |
+
verify 6: accepted 5/5 (K=6) + correction -> +6 tokens (162.6 ms) cpos=101
|
| 692 |
+
[margins] 4.88 1.00 0.67 2.09 0.21 K=2
|
| 693 |
+
verify 7: accepted 1/1 (K=2) + correction -> +2 tokens (102.2 ms) cpos=103
|
| 694 |
+
[margins] 2.01 0.47 2.13 1.42 1.72 K=2
|
| 695 |
+
verify 8: accepted 1/1 (K=2) + correction -> +2 tokens (104.1 ms) cpos=105
|
| 696 |
+
[margins] 8.79 7.59 6.26 5.95 1.51 K=6
|
| 697 |
+
verify 9: accepted 5/5 (K=6) + correction -> +6 tokens (159.6 ms) cpos=111
|
| 698 |
+
[margins] 6.74 7.68 5.77 9.72 1.91 K=6
|
| 699 |
+
verify 10: accepted 5/5 (K=6) + correction -> +6 tokens (166.9 ms) cpos=117
|
| 700 |
+
[margins] 13.68 10.26 1.38 1.61 1.56 K=3
|
| 701 |
+
verify 11: accepted 2/2 (K=3) + correction -> +3 tokens (118.8 ms) cpos=120
|
| 702 |
+
[margins] 3.49 0.79 1.66 0.04 0.83 K=2
|
| 703 |
+
verify 12: accepted 1/1 (K=2) + correction -> +2 tokens (103.3 ms) cpos=122
|
| 704 |
+
[margins] 7.64 3.38 7.01 1.86 2.70 K=6
|
| 705 |
+
verify 13: accepted 3/5 (K=6) + correction -> +4 tokens (181.4 ms) cpos=126
|
| 706 |
+
[margins] 11.15 6.24 5.38 10.00 7.97 K=6
|
| 707 |
+
verify 14: accepted 5/5 (K=6) + correction -> +6 tokens (181.4 ms) cpos=132
|
| 708 |
+
[margins] 11.30 12.87 1.84 14.53 10.03 K=6
|
| 709 |
+
verify 15: accepted 5/5 (K=6) + correction -> +6 tokens (160.5 ms) cpos=138
|
| 710 |
+
[margins] 7.88 1.84 1.91 2.81 4.62 K=6
|
| 711 |
+
verify 16: accepted 1/5 (K=6) + correction -> +2 tokens (166.4 ms) cpos=140
|
| 712 |
+
[margins] 7.95 1.10 5.85 0.24 4.15 K=2
|
| 713 |
+
verify 17: accepted 0/1 (K=2) + correction -> +1 tokens (100.8 ms) cpos=141
|
| 714 |
+
[margins] 7.77 5.28 2.71 0.13 0.58 K=4
|
| 715 |
+
verify 18: accepted 2/3 (K=4) + correction -> +3 tokens (128.6 ms) cpos=144
|
| 716 |
+
[margins] 10.19 5.01 4.45 5.58 0.32 K=5
|
| 717 |
+
verify 19: accepted 4/4 (K=5) + correction -> +5 tokens (145.4 ms) cpos=149
|
| 718 |
+
[margins] 14.87 10.57 6.46 5.74 11.06 K=6
|
| 719 |
+
verify 20: accepted 5/5 (K=6) + correction -> +6 tokens (160.6 ms) cpos=155
|
| 720 |
+
[margins] 14.67 10.82 10.49 8.55 1.97 K=6
|
| 721 |
+
verify 21: accepted 4/5 (K=6) + correction -> +5 tokens (166.9 ms) cpos=160
|
| 722 |
+
[margins] 9.28 0.74 10.50 5.60 4.63 K=2
|
| 723 |
+
verify 22: accepted 0/1 (K=2) + correction -> +1 tokens (101.1 ms) cpos=161
|
| 724 |
+
[margins] 9.36 5.67 1.05 4.87 0.98 K=3
|
| 725 |
+
verify 23: accepted 2/2 (K=3) + correction -> +3 tokens (116.7 ms) cpos=164
|
| 726 |
+
[margins] 9.75 8.31 3.37 9.73 6.23 K=6
|
| 727 |
+
verify 24: accepted 5/5 (K=6) + correction -> +6 tokens (161.3 ms) cpos=170
|
| 728 |
+
[margins] 2.59 7.34 10.23 8.86 0.35 K=5
|
| 729 |
+
verify 25: accepted 4/4 (K=5) + correction -> +5 tokens (145.7 ms) cpos=175
|
| 730 |
+
[margins] 16.11 12.83 10.96 7.59 0.81 K=5
|
| 731 |
+
verify 26: accepted 4/4 (K=5) + correction -> +5 tokens (149.1 ms) cpos=180
|
| 732 |
+
[margins] 14.87 14.86 5.04 1.73 7.75 K=6
|
| 733 |
+
verify 27: accepted 5/5 (K=6) + correction -> +6 tokens (160.7 ms) cpos=186
|
| 734 |
+
[margins] 6.19 9.10 3.70 5.96 2.30 K=6
|
| 735 |
+
verify 28: accepted 5/5 (K=6) + correction -> +6 tokens (167.1 ms) cpos=192
|
| 736 |
+
[margins] 12.31 14.42 10.34 8.64 11.03 K=6
|
| 737 |
+
verify 29: accepted 5/5 (K=6) + correction -> +6 tokens (161.4 ms) cpos=198
|
| 738 |
+
[margins] 8.13 11.15 10.75 12.43 3.06 K=6
|
| 739 |
+
verify 30: accepted 5/5 (K=6) + correction -> +6 tokens (163.7 ms) cpos=204
|
| 740 |
+
[margins] 9.40 4.83 3.16 6.50 3.16 K=6
|
| 741 |
+
verify 31: accepted 5/5 (K=6) + correction -> +6 tokens (160.8 ms) cpos=210
|
| 742 |
+
[margins] 8.83 8.57 7.23 8.44 0.37 K=5
|
| 743 |
+
verify 32: accepted 4/4 (K=5) + correction -> +5 tokens (144.9 ms) cpos=215
|
| 744 |
+
[margins] 14.63 12.40 9.41 8.43 0.16 K=5
|
| 745 |
+
verify 33: accepted 4/4 (K=5) + correction -> +5 tokens (151.0 ms) cpos=220
|
| 746 |
+
[margins] 17.46 12.69 1.26 0.01 0.67 K=3
|
| 747 |
+
verify 34: accepted 2/2 (K=3) + correction -> +3 tokens (112.3 ms) cpos=223
|
| 748 |
+
[margins] 2.60 6.39 1.59 5.72 3.25 K=6
|
| 749 |
+
verify 35: accepted 5/5 (K=6) + correction -> +6 tokens (168.1 ms) cpos=229
|
| 750 |
+
[margins] 18.71 9.60 8.81 9.68 9.67 K=6
|
| 751 |
+
verify 36: accepted 5/5 (K=6) + correction -> +6 tokens (165.8 ms) cpos=235
|
| 752 |
+
[margins] 7.27 10.56 7.04 6.56 0.10 K=5
|
| 753 |
+
verify 37: accepted 4/4 (K=5) + correction -> +5 tokens (151.7 ms) cpos=240
|
| 754 |
+
[margins] 18.01 13.21 4.02 1.45 6.55 K=4
|
| 755 |
+
verify 38: accepted 3/3 (K=4) + correction -> +4 tokens (130.3 ms) cpos=244
|
| 756 |
+
[margins] 9.80 5.24 6.07 4.29 0.22 K=5
|
| 757 |
+
verify 39: accepted 4/4 (K=5) + correction -> +5 tokens (145.6 ms) cpos=249
|
| 758 |
+
[margins] 15.49 11.07 7.06 11.24 10.93 K=6
|
| 759 |
+
verify 40: accepted 5/5 (K=6) + correction -> +6 tokens (161.4 ms) cpos=255
|
| 760 |
+
[margins] 14.04 12.09 10.84 6.90 6.53 K=6
|
| 761 |
+
verify 41: accepted 5/5 (K=6) + correction -> +6 tokens (183.3 ms) cpos=261
|
| 762 |
+
[margins] 14.39 8.51 6.01 7.52 0.41 K=5
|
| 763 |
+
verify 42: accepted 4/4 (K=5) + correction -> +5 tokens (146.4 ms) cpos=266
|
| 764 |
+
[margins] 11.12 10.64 0.15 4.55 5.12 K=3
|
| 765 |
+
verify 43: accepted 2/2 (K=3) + correction -> +3 tokens (120.5 ms) cpos=269
|
| 766 |
+
[margins] 14.58 11.53 7.02 9.45 7.94 K=6
|
| 767 |
+
verify 44: accepted 5/5 (K=6) + correction -> +6 tokens (165.8 ms) cpos=275
|
| 768 |
+
[margins] 13.62 14.08 10.46 8.72 8.78 K=6
|
| 769 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (168.7 ms) cpos=281
|
| 770 |
+
[margins] 13.75 5.82 5.30 7.33 0.42 K=5
|
| 771 |
+
verify 46: accepted 4/4 (K=5) + correction -> +5 tokens (145.7 ms) cpos=286
|
| 772 |
+
|
| 773 |
+
[spec] generated 204 tokens over 46 verifies: mean tokens/verify = 4.43 (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: 32.3 ms/tok = 30.94 tok/s (vs base M=1 71.5 ms/tok = 13.99 tok/s -> 2.21x)
|
| 776 |
+
[decode] PREFILL: 14 positions in 284.7 ms = 49.2 tok/s (20.338 ms/tok)
|
| 777 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=6 s=15)...
|
| 778 |
+
[margins] 0.53 3.09 0.45 0.94 0.17 K=3
|
| 779 |
+
verify 1: accepted 1/2 (K=3) + correction -> +2 tokens (115.6 ms) cpos=16
|
| 780 |
+
[margins] 3.55 0.19 2.32 0.84 1.15 K=2
|
| 781 |
+
verify 2: accepted 1/1 (K=2) + correction -> +2 tokens (99.2 ms) cpos=18
|
| 782 |
+
[margins] 2.62 0.03 1.78 1.22 2.10 K=2
|
| 783 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (103.2 ms) cpos=20
|
| 784 |
+
[margins] 2.21 1.22 1.78 2.74 2.29 K=2
|
| 785 |
+
verify 4: accepted 1/1 (K=2) + correction -> +2 tokens (98.4 ms) cpos=22
|
| 786 |
+
[margins] 4.08 2.60 2.14 2.81 3.27 K=6
|
| 787 |
+
verify 5: accepted 3/5 (K=6) + correction -> +4 tokens (152.1 ms) cpos=26
|
| 788 |
+
[margins] 2.31 4.44 3.74 2.08 2.98 K=6
|
| 789 |
+
verify 6: accepted 4/5 (K=6) + correction -> +5 tokens (149.1 ms) cpos=31
|
| 790 |
+
[margins] 0.46 9.02 3.74 1.60 4.18 K=6
|
| 791 |
+
verify 7: accepted 0/5 (K=6) + correction -> +1 tokens (154.6 ms) cpos=32
|
| 792 |
+
[margins] 7.64 1.53 0.15 6.23 3.21 K=3
|
| 793 |
+
verify 8: accepted 1/2 (K=3) + correction -> +2 tokens (109.2 ms) cpos=34
|
| 794 |
+
[margins] 2.19 5.70 1.40 0.06 3.33 K=3
|
| 795 |
+
verify 9: accepted 2/2 (K=3) + correction -> +3 tokens (110.5 ms) cpos=37
|
| 796 |
+
[margins] 11.21 6.26 2.86 4.53 6.73 K=6
|
| 797 |
+
verify 10: accepted 5/5 (K=6) + correction -> +6 tokens (148.6 ms) cpos=43
|
| 798 |
+
[margins] 12.94 7.70 8.10 10.64 7.32 K=6
|
| 799 |
+
verify 11: accepted 5/5 (K=6) + correction -> +6 tokens (156.3 ms) cpos=49
|
| 800 |
+
[margins] 15.18 10.16 9.12 8.98 10.96 K=6
|
| 801 |
+
verify 12: accepted 5/5 (K=6) + correction -> +6 tokens (152.0 ms) cpos=55
|
| 802 |
+
[margins] 12.79 9.70 9.87 7.93 9.89 K=6
|
| 803 |
+
verify 13: accepted 5/5 (K=6) + correction -> +6 tokens (155.2 ms) cpos=61
|
| 804 |
+
[margins] 17.09 9.66 10.66 9.59 9.44 K=6
|
| 805 |
+
verify 14: accepted 5/5 (K=6) + correction -> +6 tokens (152.3 ms) cpos=67
|
| 806 |
+
[margins] 15.90 9.77 8.41 9.38 8.92 K=6
|
| 807 |
+
verify 15: accepted 5/5 (K=6) + correction -> +6 tokens (159.1 ms) cpos=73
|
| 808 |
+
[margins] 14.72 10.35 11.26 7.45 9.76 K=6
|
| 809 |
+
verify 16: accepted 5/5 (K=6) + correction -> +6 tokens (153.1 ms) cpos=79
|
| 810 |
+
[margins] 16.00 9.95 11.11 12.39 11.24 K=6
|
| 811 |
+
verify 17: accepted 5/5 (K=6) + correction -> +6 tokens (157.9 ms) cpos=85
|
| 812 |
+
[margins] 15.20 10.54 9.15 11.01 9.73 K=6
|
| 813 |
+
verify 18: accepted 5/5 (K=6) + correction -> +6 tokens (155.8 ms) cpos=91
|
| 814 |
+
[margins] 15.15 10.39 9.93 9.33 11.53 K=6
|
| 815 |
+
verify 19: accepted 5/5 (K=6) + correction -> +6 tokens (162.0 ms) cpos=97
|
| 816 |
+
[margins] 16.14 10.55 10.85 10.70 11.82 K=6
|
| 817 |
+
verify 20: accepted 5/5 (K=6) + correction -> +6 tokens (153.6 ms) cpos=103
|
| 818 |
+
[margins] 14.03 10.13 11.72 11.84 10.00 K=6
|
| 819 |
+
verify 21: accepted 5/5 (K=6) + correction -> +6 tokens (162.4 ms) cpos=109
|
| 820 |
+
[margins] 15.96 10.19 11.97 12.93 9.87 K=6
|
| 821 |
+
verify 22: accepted 5/5 (K=6) + correction -> +6 tokens (156.5 ms) cpos=115
|
| 822 |
+
[margins] 13.38 10.17 11.46 11.99 10.90 K=6
|
| 823 |
+
verify 23: accepted 5/5 (K=6) + correction -> +6 tokens (160.5 ms) cpos=121
|
| 824 |
+
[margins] 14.36 10.18 12.57 9.23 10.39 K=6
|
| 825 |
+
verify 24: accepted 5/5 (K=6) + correction -> +6 tokens (157.7 ms) cpos=127
|
| 826 |
+
[margins] 15.53 9.88 11.45 10.98 11.81 K=6
|
| 827 |
+
verify 25: accepted 5/5 (K=6) + correction -> +6 tokens (175.9 ms) cpos=133
|
| 828 |
+
[margins] 15.87 9.15 11.39 8.47 10.39 K=6
|
| 829 |
+
verify 26: accepted 5/5 (K=6) + correction -> +6 tokens (153.8 ms) cpos=139
|
| 830 |
+
[margins] 12.29 9.83 11.75 11.52 11.08 K=6
|
| 831 |
+
verify 27: accepted 5/5 (K=6) + correction -> +6 tokens (160.9 ms) cpos=145
|
| 832 |
+
[margins] 15.57 9.50 11.03 10.35 9.40 K=6
|
| 833 |
+
verify 28: accepted 5/5 (K=6) + correction -> +6 tokens (156.2 ms) cpos=151
|
| 834 |
+
[margins] 13.57 9.86 12.59 9.42 11.59 K=6
|
| 835 |
+
verify 29: accepted 5/5 (K=6) + correction -> +6 tokens (160.1 ms) cpos=157
|
| 836 |
+
[margins] 14.57 9.25 9.94 13.17 10.43 K=6
|
| 837 |
+
verify 30: accepted 5/5 (K=6) + correction -> +6 tokens (159.4 ms) cpos=163
|
| 838 |
+
[margins] 18.14 8.91 10.71 9.71 9.47 K=6
|
| 839 |
+
verify 31: accepted 5/5 (K=6) + correction -> +6 tokens (161.1 ms) cpos=169
|
| 840 |
+
[margins] 15.19 10.42 11.53 9.09 12.17 K=6
|
| 841 |
+
verify 32: accepted 5/5 (K=6) + correction -> +6 tokens (158.4 ms) cpos=175
|
| 842 |
+
[margins] 16.20 8.96 10.60 8.10 10.14 K=6
|
| 843 |
+
verify 33: accepted 5/5 (K=6) + correction -> +6 tokens (162.2 ms) cpos=181
|
| 844 |
+
[margins] 16.98 9.84 10.48 9.08 10.75 K=6
|
| 845 |
+
verify 34: accepted 5/5 (K=6) + correction -> +6 tokens (159.3 ms) cpos=187
|
| 846 |
+
[margins] 15.42 9.92 12.21 10.69 7.97 K=6
|
| 847 |
+
verify 35: accepted 5/5 (K=6) + correction -> +6 tokens (163.8 ms) cpos=193
|
| 848 |
+
[margins] 15.54 9.81 10.89 9.71 9.03 K=6
|
| 849 |
+
verify 36: accepted 5/5 (K=6) + correction -> +6 tokens (158.1 ms) cpos=199
|
| 850 |
+
[margins] 18.59 9.65 11.31 11.17 8.07 K=6
|
| 851 |
+
verify 37: accepted 5/5 (K=6) + correction -> +6 tokens (162.9 ms) cpos=205
|
| 852 |
+
[margins] 14.82 9.94 10.97 10.41 9.52 K=6
|
| 853 |
+
verify 38: accepted 5/5 (K=6) + correction -> +6 tokens (158.2 ms) cpos=211
|
| 854 |
+
[margins] 17.07 9.32 11.00 7.70 10.56 K=6
|
| 855 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (163.2 ms) cpos=217
|
| 856 |
+
|
| 857 |
+
[spec] generated 203 tokens over 39 verifies: mean tokens/verify = 5.21 (block=5, max 6)
|
| 858 |
+
[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
|
| 859 |
+
[spec] SPEC-DECODE: 28.5 ms/tok = 35.06 tok/s (vs base M=1 71.5 ms/tok = 13.99 tok/s -> 2.51x)
|
| 860 |
+
[decode] PREFILL: 37 positions in 663.6 ms = 55.8 tok/s (17.934 ms/tok)
|
| 861 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=7 s=38)...
|
| 862 |
+
[margins] 0.70 1.59 0.03 0.61 1.27 K=3
|
| 863 |
+
verify 1: accepted 0/2 (K=3) + correction -> +1 tokens (116.6 ms) cpos=38
|
| 864 |
+
[margins] 0.02 5.81 0.07 0.02 0.02 K=3
|
| 865 |
+
verify 2: accepted 0/2 (K=3) + correction -> +1 tokens (111.4 ms) cpos=39
|
| 866 |
+
[margins] 1.63 0.36 5.16 0.50 1.26 K=2
|
| 867 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (99.7 ms) cpos=41
|
| 868 |
+
[margins] 2.81 0.33 0.50 5.77 0.68 K=2
|
| 869 |
+
verify 4: accepted 1/1 (K=2) + correction -> +2 tokens (94.9 ms) cpos=43
|
| 870 |
+
[margins] 1.20 1.88 0.17 0.05 0.09 K=3
|
| 871 |
+
verify 5: accepted 0/2 (K=3) + correction -> +1 tokens (111.5 ms) cpos=44
|
| 872 |
+
[margins] 0.05 0.09 0.50 0.04 0.10 K=2
|
| 873 |
+
verify 6: accepted 1/1 (K=2) + correction -> +2 tokens (95.5 ms) cpos=46
|
| 874 |
+
[margins] 0.97 1.13 1.88 0.01 0.20 K=2
|
| 875 |
+
verify 7: accepted 0/1 (K=2) + correction -> +1 tokens (101.2 ms) cpos=47
|
| 876 |
+
[margins] 1.39 1.85 0.43 2.56 0.73 K=3
|
| 877 |
+
verify 8: accepted 1/2 (K=3) + correction -> +2 tokens (113.8 ms) cpos=49
|
| 878 |
+
[margins] 7.49 6.73 6.03 1.93 0.11 K=5
|
| 879 |
+
verify 9: accepted 4/4 (K=5) + correction -> +5 tokens (138.4 ms) cpos=54
|
| 880 |
+
[margins] 0.25 2.35 2.80 3.25 1.16 K=5
|
| 881 |
+
verify 10: accepted 2/4 (K=5) + correction -> +3 tokens (138.8 ms) cpos=57
|
| 882 |
+
[margins] 2.84 0.96 0.73 1.62 0.22 K=2
|
| 883 |
+
verify 11: accepted 1/1 (K=2) + correction -> +2 tokens (97.4 ms) cpos=59
|
| 884 |
+
[margins] 3.71 2.44 0.77 0.30 0.66 K=3
|
| 885 |
+
verify 12: accepted 2/2 (K=3) + correction -> +3 tokens (113.7 ms) cpos=62
|
| 886 |
+
[margins] 0.99 1.63 2.25 0.32 2.71 K=4
|
| 887 |
+
verify 13: accepted 3/3 (K=4) + correction -> +4 tokens (125.9 ms) cpos=66
|
| 888 |
+
[margins] 13.30 2.58 5.99 0.98 1.24 K=4
|
| 889 |
+
verify 14: accepted 3/3 (K=4) + correction -> +4 tokens (128.7 ms) cpos=70
|
| 890 |
+
[margins] 1.38 0.74 0.77 2.65 0.63 K=2
|
| 891 |
+
verify 15: accepted 1/1 (K=2) + correction -> +2 tokens (101.9 ms) cpos=72
|
| 892 |
+
[margins] 2.42 6.28 0.11 2.17 0.67 K=3
|
| 893 |
+
verify 16: accepted 2/2 (K=3) + correction -> +3 tokens (108.3 ms) cpos=75
|
| 894 |
+
[margins] 2.54 8.84 0.86 3.09 0.26 K=3
|
| 895 |
+
verify 17: accepted 2/2 (K=3) + correction -> +3 tokens (111.4 ms) cpos=78
|
| 896 |
+
[margins] 7.93 7.63 6.44 7.42 9.10 K=6
|
| 897 |
+
verify 18: accepted 5/5 (K=6) + correction -> +6 tokens (160.2 ms) cpos=84
|
| 898 |
+
[margins] 7.65 8.49 5.89 3.00 0.63 K=5
|
| 899 |
+
verify 19: accepted 4/4 (K=5) + correction -> +5 tokens (141.4 ms) cpos=89
|
| 900 |
+
[margins] 7.26 6.42 4.10 0.58 0.53 K=4
|
| 901 |
+
verify 20: accepted 3/3 (K=4) + correction -> +4 tokens (128.2 ms) cpos=93
|
| 902 |
+
[margins] 4.87 3.32 2.36 1.10 0.17 K=4
|
| 903 |
+
verify 21: accepted 3/3 (K=4) + correction -> +4 tokens (126.3 ms) cpos=97
|
| 904 |
+
[margins] 9.72 12.06 10.28 9.68 3.82 K=6
|
| 905 |
+
verify 22: accepted 5/5 (K=6) + correction -> +6 tokens (159.6 ms) cpos=103
|
| 906 |
+
[margins] 9.84 4.14 2.91 0.98 9.67 K=4
|
| 907 |
+
verify 23: accepted 3/3 (K=4) + correction -> +4 tokens (130.5 ms) cpos=107
|
| 908 |
+
[margins] 4.92 3.14 10.27 1.89 3.97 K=6
|
| 909 |
+
verify 24: accepted 3/5 (K=6) + correction -> +4 tokens (167.0 ms) cpos=111
|
| 910 |
+
[margins] 10.05 5.75 7.36 4.34 6.65 K=6
|
| 911 |
+
verify 25: accepted 5/5 (K=6) + correction -> +6 tokens (167.2 ms) cpos=117
|
| 912 |
+
[margins] 10.51 9.03 3.71 5.42 4.64 K=6
|
| 913 |
+
verify 26: accepted 5/5 (K=6) + correction -> +6 tokens (161.4 ms) cpos=123
|
| 914 |
+
[margins] 13.39 5.92 8.62 7.32 0.04 K=5
|
| 915 |
+
verify 27: accepted 4/4 (K=5) + correction -> +5 tokens (163.1 ms) cpos=128
|
| 916 |
+
[margins] 5.40 5.12 4.08 2.71 3.11 K=6
|
| 917 |
+
verify 28: accepted 3/5 (K=6) + correction -> +4 tokens (160.2 ms) cpos=132
|
| 918 |
+
[margins] 5.05 2.19 3.59 2.25 0.85 K=5
|
| 919 |
+
verify 29: accepted 4/4 (K=5) + correction -> +5 tokens (142.1 ms) cpos=137
|
| 920 |
+
[margins] 3.27 0.09 0.24 0.24 0.60 K=2
|
| 921 |
+
verify 30: accepted 1/1 (K=2) + correction -> +2 tokens (102.0 ms) cpos=139
|
| 922 |
+
[margins] 5.66 0.71 5.56 6.67 5.08 K=2
|
| 923 |
+
verify 31: accepted 1/1 (K=2) + correction -> +2 tokens (105.2 ms) cpos=141
|
| 924 |
+
[margins] 9.18 7.93 5.62 1.54 0.48 K=5
|
| 925 |
+
verify 32: accepted 4/4 (K=5) + correction -> +5 tokens (145.0 ms) cpos=146
|
| 926 |
+
[margins] 7.84 9.14 9.91 11.09 1.70 K=6
|
| 927 |
+
verify 33: accepted 4/5 (K=6) + correction -> +5 tokens (168.2 ms) cpos=151
|
| 928 |
+
[margins] 2.10 1.29 0.49 7.61 0.17 K=2
|
| 929 |
+
verify 34: accepted 1/1 (K=2) + correction -> +2 tokens (109.9 ms) cpos=153
|
| 930 |
+
[margins] 1.31 2.69 0.77 1.10 3.79 K=3
|
| 931 |
+
verify 35: accepted 0/2 (K=3) + correction -> +1 tokens (109.5 ms) cpos=154
|
| 932 |
+
[margins] 6.53 2.50 1.28 2.10 1.42 K=3
|
| 933 |
+
verify 36: accepted 1/2 (K=3) + correction -> +2 tokens (115.7 ms) cpos=156
|
| 934 |
+
[margins] 6.30 3.19 0.44 1.70 2.19 K=3
|
| 935 |
+
verify 37: accepted 1/2 (K=3) + correction -> +2 tokens (110.5 ms) cpos=158
|
| 936 |
+
[margins] 4.70 0.85 3.48 1.28 1.42 K=2
|
| 937 |
+
verify 38: accepted 1/1 (K=2) + correction -> +2 tokens (107.4 ms) cpos=160
|
| 938 |
+
[margins] 5.44 3.82 4.37 0.40 3.31 K=4
|
| 939 |
+
verify 39: accepted 3/3 (K=4) + correction -> +4 tokens (124.0 ms) cpos=164
|
| 940 |
+
[margins] 5.02 7.90 6.10 3.80 4.65 K=6
|
| 941 |
+
verify 40: accepted 5/5 (K=6) + correction -> +6 tokens (149.4 ms) cpos=170
|
| 942 |
+
[margins] 3.93 9.37 3.85 5.33 4.60 K=6
|
| 943 |
+
verify 41: accepted 5/5 (K=6) + correction -> +6 tokens (154.8 ms) cpos=176
|
| 944 |
+
[margins] 3.99 8.09 3.92 6.60 5.39 K=6
|
| 945 |
+
verify 42: accepted 5/5 (K=6) + correction -> +6 tokens (150.4 ms) cpos=182
|
| 946 |
+
[margins] 3.36 8.74 4.97 7.39 5.80 K=6
|
| 947 |
+
verify 43: accepted 5/5 (K=6) + correction -> +6 tokens (155.4 ms) cpos=188
|
| 948 |
+
[margins] 2.67 8.65 4.97 6.18 5.71 K=6
|
| 949 |
+
verify 44: accepted 5/5 (K=6) + correction -> +6 tokens (150.6 ms) cpos=194
|
| 950 |
+
[margins] 2.54 8.14 4.54 6.41 5.21 K=6
|
| 951 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (155.2 ms) cpos=200
|
| 952 |
+
[margins] 3.45 8.92 4.69 5.34 4.57 K=6
|
| 953 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (151.2 ms) cpos=206
|
| 954 |
+
[margins] 3.91 8.12 4.03 4.74 5.54 K=6
|
| 955 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (156.4 ms) cpos=212
|
| 956 |
+
[margins] 3.34 6.86 4.37 4.16 5.20 K=6
|
| 957 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (149.2 ms) cpos=218
|
| 958 |
+
[margins] 3.90 7.05 4.89 3.78 5.48 K=6
|
| 959 |
+
verify 49: accepted 5/5 (K=6) + correction -> +6 tokens (156.1 ms) cpos=224
|
| 960 |
+
[margins] 4.14 7.19 4.34 3.83 5.06 K=6
|
| 961 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (150.0 ms) cpos=230
|
| 962 |
+
[margins] 4.07 6.49 4.86 2.97 5.66 K=6
|
| 963 |
+
verify 51: accepted 0/5 (K=6) + correction -> +1 tokens (156.6 ms) cpos=231
|
| 964 |
+
[margins] 9.25 1.93 3.54 5.73 1.32 K=5
|
| 965 |
+
verify 52: accepted 0/4 (K=5) + correction -> +1 tokens (143.5 ms) cpos=232
|
| 966 |
+
[margins] 5.83 2.47 7.65 1.78 0.59 K=5
|
| 967 |
+
verify 53: accepted 1/4 (K=5) + correction -> +2 tokens (140.6 ms) cpos=234
|
| 968 |
+
[margins] 2.68 1.47 2.85 1.57 1.17 K=2
|
| 969 |
+
verify 54: accepted 1/1 (K=2) + correction -> +2 tokens (104.3 ms) cpos=236
|
| 970 |
+
[margins] 4.04 0.04 6.10 0.59 0.14 K=2
|
| 971 |
+
verify 55: accepted 0/1 (K=2) + correction -> +1 tokens (100.8 ms) cpos=237
|
| 972 |
+
|
| 973 |
+
[spec] generated 200 tokens over 55 verifies: mean tokens/verify = 3.64 (block=5, max 6)
|
| 974 |
+
[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
|
| 975 |
+
[spec] SPEC-DECODE: 35.8 ms/tok = 27.94 tok/s (vs base M=1 71.5 ms/tok = 13.99 tok/s -> 2.00x)
|
| 976 |
+
[decode] PREFILL: 12 positions in 250.9 ms = 47.8 tok/s (20.907 ms/tok)
|
| 977 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=8 s=13)...
|
| 978 |
+
[margins] 2.75 1.00 0.20 0.17 0.38 K=2
|
| 979 |
+
verify 1: accepted 1/1 (K=2) + correction -> +2 tokens (99.2 ms) cpos=14
|
| 980 |
+
[margins] 0.33 6.66 2.87 0.68 6.36 K=4
|
| 981 |
+
verify 2: accepted 0/3 (K=4) + correction -> +1 tokens (127.8 ms) cpos=15
|
| 982 |
+
[margins] 0.37 0.83 1.89 0.16 3.54 K=2
|
| 983 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (102.6 ms) cpos=17
|
| 984 |
+
[margins] 0.57 0.05 0.82 2.51 0.04 K=2
|
| 985 |
+
verify 4: accepted 1/1 (K=2) + correction -> +2 tokens (98.3 ms) cpos=19
|
| 986 |
+
[margins] 2.30 0.09 2.86 0.34 2.94 K=2
|
| 987 |
+
verify 5: accepted 1/1 (K=2) + correction -> +2 tokens (102.4 ms) cpos=21
|
| 988 |
+
[margins] 1.66 0.27 3.32 1.05 3.32 K=2
|
| 989 |
+
verify 6: accepted 1/1 (K=2) + correction -> +2 tokens (98.4 ms) cpos=23
|
| 990 |
+
[margins] 2.41 0.04 1.43 0.74 3.43 K=2
|
| 991 |
+
verify 7: accepted 1/1 (K=2) + correction -> +2 tokens (102.7 ms) cpos=25
|
| 992 |
+
[margins] 3.08 0.53 5.08 0.59 4.15 K=2
|
| 993 |
+
verify 8: accepted 1/1 (K=2) + correction -> +2 tokens (98.7 ms) cpos=27
|
| 994 |
+
[margins] 3.73 1.07 5.31 1.34 4.79 K=2
|
| 995 |
+
verify 9: accepted 1/1 (K=2) + correction -> +2 tokens (102.6 ms) cpos=29
|
| 996 |
+
[margins] 5.15 0.66 4.81 1.01 4.48 K=2
|
| 997 |
+
verify 10: accepted 1/1 (K=2) + correction -> +2 tokens (98.7 ms) cpos=31
|
| 998 |
+
[margins] 5.79 1.31 4.87 1.54 4.35 K=2
|
| 999 |
+
verify 11: accepted 1/1 (K=2) + correction -> +2 tokens (102.7 ms) cpos=33
|
| 1000 |
+
[margins] 5.70 0.75 4.75 1.40 3.95 K=2
|
| 1001 |
+
verify 12: accepted 1/1 (K=2) + correction -> +2 tokens (99.2 ms) cpos=35
|
| 1002 |
+
[margins] 6.22 0.87 5.74 1.41 4.68 K=2
|
| 1003 |
+
verify 13: accepted 1/1 (K=2) + correction -> +2 tokens (102.5 ms) cpos=37
|
| 1004 |
+
[margins] 5.69 0.72 5.02 1.42 3.92 K=2
|
| 1005 |
+
verify 14: accepted 1/1 (K=2) + correction -> +2 tokens (99.0 ms) cpos=39
|
| 1006 |
+
[margins] 6.48 0.46 5.96 1.14 4.82 K=2
|
| 1007 |
+
verify 15: accepted 1/1 (K=2) + correction -> +2 tokens (102.6 ms) cpos=41
|
| 1008 |
+
[margins] 6.34 0.80 5.22 1.51 4.02 K=2
|
| 1009 |
+
verify 16: accepted 1/1 (K=2) + correction -> +2 tokens (99.3 ms) cpos=43
|
| 1010 |
+
[margins] 6.79 0.99 5.89 2.04 4.43 K=2
|
| 1011 |
+
verify 17: accepted 1/1 (K=2) + correction -> +2 tokens (103.4 ms) cpos=45
|
| 1012 |
+
[margins] 5.97 1.49 4.39 1.29 3.44 K=2
|
| 1013 |
+
verify 18: accepted 0/1 (K=2) + correction -> +1 tokens (96.1 ms) cpos=46
|
| 1014 |
+
[margins] 5.34 3.56 5.86 0.35 0.41 K=4
|
| 1015 |
+
verify 19: accepted 3/3 (K=4) + correction -> +4 tokens (126.4 ms) cpos=50
|
| 1016 |
+
[margins] 2.53 2.71 0.34 2.28 2.94 K=3
|
| 1017 |
+
verify 20: accepted 2/2 (K=3) + correction -> +3 tokens (113.2 ms) cpos=53
|
| 1018 |
+
[margins] 7.98 8.65 0.17 3.71 0.28 K=3
|
| 1019 |
+
verify 21: accepted 2/2 (K=3) + correction -> +3 tokens (112.0 ms) cpos=56
|
| 1020 |
+
[margins] 2.45 0.09 1.72 2.65 2.79 K=2
|
| 1021 |
+
verify 22: accepted 1/1 (K=2) + correction -> +2 tokens (100.2 ms) cpos=58
|
| 1022 |
+
[margins] 0.33 6.60 1.43 3.30 2.30 K=3
|
| 1023 |
+
verify 23: accepted 0/2 (K=3) + correction -> +1 tokens (110.4 ms) cpos=59
|
| 1024 |
+
[margins] 0.36 2.40 0.54 6.22 0.05 K=3
|
| 1025 |
+
verify 24: accepted 1/2 (K=3) + correction -> +2 tokens (113.3 ms) cpos=61
|
| 1026 |
+
[margins] 5.48 7.69 6.32 4.11 8.12 K=6
|
| 1027 |
+
verify 25: accepted 5/5 (K=6) + correction -> +6 tokens (156.1 ms) cpos=67
|
| 1028 |
+
[margins] 7.96 10.33 0.33 1.45 0.95 K=3
|
| 1029 |
+
verify 26: accepted 2/2 (K=3) + correction -> +3 tokens (114.5 ms) cpos=70
|
| 1030 |
+
[margins] 2.79 2.36 0.47 4.09 1.44 K=3
|
| 1031 |
+
verify 27: accepted 0/2 (K=3) + correction -> +1 tokens (115.0 ms) cpos=71
|
| 1032 |
+
[margins] 1.71 2.67 3.89 1.96 2.32 K=6
|
| 1033 |
+
verify 28: accepted 0/5 (K=6) + correction -> +1 tokens (163.3 ms) cpos=72
|
| 1034 |
+
[margins] 3.51 3.68 3.83 6.94 3.07 K=6
|
| 1035 |
+
verify 29: accepted 5/5 (K=6) + correction -> +6 tokens (157.4 ms) cpos=78
|
| 1036 |
+
[margins] 7.05 10.29 8.38 0.90 0.68 K=4
|
| 1037 |
+
verify 30: accepted 3/3 (K=4) + correction -> +4 tokens (128.7 ms) cpos=82
|
| 1038 |
+
[margins] 3.83 7.11 4.08 5.29 1.12 K=5
|
| 1039 |
+
verify 31: accepted 4/4 (K=5) + correction -> +5 tokens (139.7 ms) cpos=87
|
| 1040 |
+
[margins] 7.94 4.92 7.43 4.79 9.97 K=6
|
| 1041 |
+
verify 32: accepted 5/5 (K=6) + correction -> +6 tokens (163.1 ms) cpos=93
|
| 1042 |
+
[margins] 2.41 4.76 6.92 4.63 5.86 K=6
|
| 1043 |
+
verify 33: accepted 5/5 (K=6) + correction -> +6 tokens (157.2 ms) cpos=99
|
| 1044 |
+
[margins] 7.86 4.07 6.68 5.78 8.18 K=6
|
| 1045 |
+
verify 34: accepted 5/5 (K=6) + correction -> +6 tokens (165.8 ms) cpos=105
|
| 1046 |
+
[margins] 2.49 4.71 5.00 6.56 6.64 K=6
|
| 1047 |
+
verify 35: accepted 5/5 (K=6) + correction -> +6 tokens (159.0 ms) cpos=111
|
| 1048 |
+
[margins] 7.11 4.43 3.55 2.72 6.24 K=6
|
| 1049 |
+
verify 36: accepted 5/5 (K=6) + correction -> +6 tokens (164.8 ms) cpos=117
|
| 1050 |
+
[margins] 3.31 6.43 8.01 8.34 7.77 K=6
|
| 1051 |
+
verify 37: accepted 5/5 (K=6) + correction -> +6 tokens (158.5 ms) cpos=123
|
| 1052 |
+
[margins] 10.91 4.84 9.61 5.38 12.63 K=6
|
| 1053 |
+
verify 38: accepted 5/5 (K=6) + correction -> +6 tokens (179.6 ms) cpos=129
|
| 1054 |
+
[margins] 3.89 5.10 9.12 7.38 5.05 K=6
|
| 1055 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (162.0 ms) cpos=135
|
| 1056 |
+
[margins] 10.03 6.48 9.81 5.03 10.76 K=6
|
| 1057 |
+
verify 40: accepted 5/5 (K=6) + correction -> +6 tokens (168.7 ms) cpos=141
|
| 1058 |
+
[margins] 3.76 6.69 6.47 8.40 7.78 K=6
|
| 1059 |
+
verify 41: accepted 5/5 (K=6) + correction -> +6 tokens (161.3 ms) cpos=147
|
| 1060 |
+
[margins] 8.99 3.35 6.89 4.19 8.54 K=6
|
| 1061 |
+
verify 42: accepted 5/5 (K=6) + correction -> +6 tokens (167.2 ms) cpos=153
|
| 1062 |
+
[margins] 2.88 7.04 6.51 4.95 5.13 K=6
|
| 1063 |
+
verify 43: accepted 5/5 (K=6) + correction -> +6 tokens (162.5 ms) cpos=159
|
| 1064 |
+
[margins] 7.32 4.28 3.54 3.00 8.26 K=6
|
| 1065 |
+
verify 44: accepted 5/5 (K=6) + correction -> +6 tokens (166.1 ms) cpos=165
|
| 1066 |
+
[margins] 3.38 5.89 4.80 7.02 6.18 K=6
|
| 1067 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (160.3 ms) cpos=171
|
| 1068 |
+
[margins] 10.74 6.38 9.90 5.03 10.46 K=6
|
| 1069 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (168.0 ms) cpos=177
|
| 1070 |
+
[margins] 4.34 4.82 7.48 6.66 8.75 K=6
|
| 1071 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (160.2 ms) cpos=183
|
| 1072 |
+
[margins] 9.50 6.65 9.90 3.48 12.31 K=6
|
| 1073 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (168.3 ms) cpos=189
|
| 1074 |
+
[margins] 4.26 5.76 8.87 7.82 8.80 K=6
|
| 1075 |
+
verify 49: accepted 5/5 (K=6) + correction -> +6 tokens (160.6 ms) cpos=195
|
| 1076 |
+
[margins] 9.91 6.53 10.76 6.32 9.55 K=6
|
| 1077 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (168.1 ms) cpos=201
|
| 1078 |
+
[margins] 4.20 5.62 7.81 7.26 5.96 K=6
|
| 1079 |
+
verify 51: accepted 5/5 (K=6) + correction -> +6 tokens (161.6 ms) cpos=207
|
| 1080 |
+
[margins] 11.14 6.88 10.22 7.88 10.18 K=6
|
| 1081 |
+
verify 52: accepted 5/5 (K=6) + correction -> +6 tokens (167.3 ms) cpos=213
|
| 1082 |
+
|
| 1083 |
+
[spec] generated 201 tokens over 52 verifies: mean tokens/verify = 3.87 (block=5, max 6)
|
| 1084 |
+
[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
|
| 1085 |
+
[spec] SPEC-DECODE: 34.4 ms/tok = 29.10 tok/s (vs base M=1 71.5 ms/tok = 13.99 tok/s -> 2.08x)
|
| 1086 |
+
|
| 1087 |
+
[blksweep] BLK passes adaptK->eff prompt | mean tok/verify | ms/tok | tok/s | vs base 13.99 tok/s
|
| 1088 |
+
[blksweep] 5 1 1.50 1.50 0 | 3.30 | 38.9 | 25.74 | 1.84x
|
| 1089 |
+
[blksweep] 5 1 1.50 1.50 1 | 4.00 | 34.2 | 29.25 | 2.09x
|
| 1090 |
+
[blksweep] 5 1 1.50 1.50 2 | 3.96 | 35.1 | 28.45 | 2.03x
|
| 1091 |
+
[blksweep] 5 1 1.50 1.50 3 | 2.66 | 45.4 | 22.01 | 1.57x
|
| 1092 |
+
[blksweep] 5 1 1.50 1.50 4 | 3.00 | 41.0 | 24.41 | 1.75x
|
| 1093 |
+
[blksweep] 5 1 1.50 1.50 5 | 4.43 | 32.3 | 30.94 | 2.21x
|
| 1094 |
+
[blksweep] 5 1 1.50 1.50 6 | 5.21 | 28.5 | 35.06 | 2.51x
|
| 1095 |
+
[blksweep] 5 1 1.50 1.50 7 | 3.64 | 35.8 | 27.94 | 2.00x
|
| 1096 |
+
[blksweep] 5 1 1.50 1.50 8 | 3.87 | 34.4 | 29.10 | 2.08x
|
| 1097 |
+
[decode] mem 106.4/122.8 GiB
|