archive arm s3recap-conf1.0: eval.log
Browse files- arms/s3recap-conf1.0/eval.log +1105 -0
arms/s3recap-conf1.0/eval.log
ADDED
|
@@ -0,0 +1,1105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 106.8/122.8 GiB
|
| 6 |
+
[decode] prefill 5 positions...
|
| 7 |
+
[f32mk] tile 4x4 (DSV4_F32MK_TILE=unset)
|
| 8 |
+
[decode] PREFILL: 5 positions in 194.6 ms = 25.7 tok/s (38.914 ms/tok)
|
| 9 |
+
[decode] prefill done. caches populated. starting decode.
|
| 10 |
+
step 0 pos 5 -> token 11111 (66.9 ms warmup)
|
| 11 |
+
step 1 pos 6 -> token 16 (66.8 ms)
|
| 12 |
+
step 2 pos 7 -> token 455 (72.7 ms)
|
| 13 |
+
step 3 pos 8 -> token 6102 (66.6 ms)
|
| 14 |
+
step 4 pos 9 -> token 294 (67.2 ms)
|
| 15 |
+
step 5 pos 10 -> token 16603 (67.0 ms)
|
| 16 |
+
step 6 pos 11 -> token 344 (73.0 ms)
|
| 17 |
+
step 7 pos 12 -> token 29168 (67.0 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 = 14.57 tok/s (M=1 steady state, 7-step avg)
|
| 22 |
+
|
| 23 |
+
[spec-verify] M=5 verify in ONE forward: 115.7 ms (= 23.1 ms/tok if all accepted vs 68.6 M=1 -> 2.96x)
|
| 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/s3recap-conf1.0/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 112.7/122.8 GiB
|
| 32 |
+
[decode] PREFILL: 5 positions in 150.1 ms = 33.3 tok/s (30.029 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] 1.47 0.95 0.52 0.62 0.05 K=2
|
| 36 |
+
verify 1: accepted 1/1 (K=2) + correction -> +2 tokens (100.7 ms) cpos=7
|
| 37 |
+
[margins] 0.57 0.13 0.62 0.46 0.19 K=2
|
| 38 |
+
verify 2: accepted 0/1 (K=2) + correction -> +1 tokens (104.7 ms) cpos=8
|
| 39 |
+
[margins] 0.53 0.67 2.15 0.75 0.18 K=2
|
| 40 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (97.7 ms) cpos=10
|
| 41 |
+
[margins] 2.42 0.72 4.06 0.13 1.63 K=2
|
| 42 |
+
verify 4: accepted 0/1 (K=2) + correction -> +1 tokens (102.6 ms) cpos=11
|
| 43 |
+
[margins] 6.74 0.52 0.77 2.98 2.42 K=2
|
| 44 |
+
verify 5: accepted 1/1 (K=2) + correction -> +2 tokens (103.0 ms) cpos=13
|
| 45 |
+
[margins] 4.46 1.86 5.04 2.56 0.25 K=5
|
| 46 |
+
verify 6: accepted 4/4 (K=5) + correction -> +5 tokens (141.3 ms) cpos=18
|
| 47 |
+
[margins] 4.67 2.52 2.75 0.83 2.68 K=4
|
| 48 |
+
verify 7: accepted 1/3 (K=4) + correction -> +2 tokens (126.8 ms) cpos=20
|
| 49 |
+
[margins] 2.94 3.16 4.72 2.56 0.68 K=5
|
| 50 |
+
verify 8: accepted 4/4 (K=5) + correction -> +5 tokens (140.3 ms) cpos=25
|
| 51 |
+
[margins] 7.02 2.26 3.35 0.51 0.17 K=4
|
| 52 |
+
verify 9: accepted 1/3 (K=4) + correction -> +2 tokens (127.4 ms) cpos=27
|
| 53 |
+
[margins] 4.10 3.33 4.82 2.91 0.55 K=5
|
| 54 |
+
verify 10: accepted 4/4 (K=5) + correction -> +5 tokens (147.2 ms) cpos=32
|
| 55 |
+
[margins] 7.48 0.10 2.52 1.29 2.62 K=2
|
| 56 |
+
verify 11: accepted 1/1 (K=2) + correction -> +2 tokens (97.1 ms) cpos=34
|
| 57 |
+
[margins] 2.52 4.47 5.57 2.16 0.23 K=5
|
| 58 |
+
verify 12: accepted 4/4 (K=5) + correction -> +5 tokens (141.8 ms) cpos=39
|
| 59 |
+
[margins] 4.25 0.16 5.00 2.00 3.59 K=2
|
| 60 |
+
verify 13: accepted 1/1 (K=2) + correction -> +2 tokens (101.3 ms) cpos=41
|
| 61 |
+
[margins] 4.12 4.43 4.64 1.08 2.23 K=4
|
| 62 |
+
verify 14: accepted 3/3 (K=4) + correction -> +4 tokens (127.5 ms) cpos=45
|
| 63 |
+
[margins] 2.87 0.50 7.12 1.50 4.52 K=2
|
| 64 |
+
verify 15: accepted 1/1 (K=2) + correction -> +2 tokens (97.9 ms) cpos=47
|
| 65 |
+
[margins] 0.87 3.79 0.69 4.72 2.45 K=3
|
| 66 |
+
verify 16: accepted 2/2 (K=3) + correction -> +3 tokens (113.8 ms) cpos=50
|
| 67 |
+
[margins] 4.90 3.36 3.76 0.92 2.55 K=4
|
| 68 |
+
verify 17: accepted 3/3 (K=4) + correction -> +4 tokens (132.6 ms) cpos=54
|
| 69 |
+
[margins] 2.75 1.30 6.55 0.93 0.81 K=2
|
| 70 |
+
verify 18: accepted 1/1 (K=2) + correction -> +2 tokens (101.7 ms) cpos=56
|
| 71 |
+
[margins] 8.84 0.20 4.14 2.81 2.33 K=2
|
| 72 |
+
verify 19: accepted 1/1 (K=2) + correction -> +2 tokens (98.0 ms) cpos=58
|
| 73 |
+
[margins] 2.43 5.35 5.58 4.39 1.84 K=6
|
| 74 |
+
verify 20: accepted 0/5 (K=6) + correction -> +1 tokens (164.8 ms) cpos=59
|
| 75 |
+
[margins] 6.14 7.50 5.64 0.94 5.90 K=4
|
| 76 |
+
verify 21: accepted 3/3 (K=4) + correction -> +4 tokens (129.9 ms) cpos=63
|
| 77 |
+
[margins] 0.46 0.36 7.31 1.38 2.52 K=2
|
| 78 |
+
verify 22: accepted 0/1 (K=2) + correction -> +1 tokens (102.7 ms) cpos=64
|
| 79 |
+
[margins] 7.07 1.14 4.25 1.21 4.41 K=2
|
| 80 |
+
verify 23: accepted 1/1 (K=2) + correction -> +2 tokens (99.2 ms) cpos=66
|
| 81 |
+
[margins] 4.86 5.29 4.32 3.20 1.17 K=5
|
| 82 |
+
verify 24: accepted 4/4 (K=5) + correction -> +5 tokens (141.5 ms) cpos=71
|
| 83 |
+
[margins] 6.36 1.97 3.24 0.65 2.79 K=4
|
| 84 |
+
verify 25: accepted 3/3 (K=4) + correction -> +4 tokens (130.7 ms) cpos=75
|
| 85 |
+
[margins] 5.80 6.63 2.72 0.49 2.72 K=4
|
| 86 |
+
verify 26: accepted 2/3 (K=4) + correction -> +3 tokens (129.5 ms) cpos=78
|
| 87 |
+
[margins] 5.26 0.23 2.48 1.05 3.19 K=2
|
| 88 |
+
verify 27: accepted 1/1 (K=2) + correction -> +2 tokens (103.5 ms) cpos=80
|
| 89 |
+
[margins] 5.70 6.20 5.03 4.38 1.21 K=5
|
| 90 |
+
verify 28: accepted 4/4 (K=5) + correction -> +5 tokens (144.9 ms) cpos=85
|
| 91 |
+
[margins] 5.53 1.24 3.87 1.95 2.92 K=2
|
| 92 |
+
verify 29: accepted 1/1 (K=2) + correction -> +2 tokens (100.2 ms) cpos=87
|
| 93 |
+
[margins] 5.44 5.19 5.03 2.64 0.65 K=5
|
| 94 |
+
verify 30: accepted 4/4 (K=5) + correction -> +5 tokens (150.5 ms) cpos=92
|
| 95 |
+
[margins] 6.86 1.09 2.83 0.30 1.93 K=2
|
| 96 |
+
verify 31: accepted 1/1 (K=2) + correction -> +2 tokens (101.4 ms) cpos=94
|
| 97 |
+
[margins] 5.17 6.46 5.21 5.76 0.67 K=5
|
| 98 |
+
verify 32: accepted 4/4 (K=5) + correction -> +5 tokens (147.0 ms) cpos=99
|
| 99 |
+
[margins] 5.19 1.40 1.13 0.58 0.91 K=2
|
| 100 |
+
verify 33: accepted 1/1 (K=2) + correction -> +2 tokens (107.3 ms) cpos=101
|
| 101 |
+
[margins] 7.02 4.11 4.37 2.00 3.53 K=6
|
| 102 |
+
verify 34: accepted 4/5 (K=6) + correction -> +5 tokens (161.8 ms) cpos=106
|
| 103 |
+
[margins] 6.12 1.17 2.82 2.04 2.58 K=2
|
| 104 |
+
verify 35: accepted 1/1 (K=2) + correction -> +2 tokens (106.3 ms) cpos=108
|
| 105 |
+
[margins] 7.28 5.51 6.63 3.27 0.77 K=5
|
| 106 |
+
verify 36: accepted 4/4 (K=5) + correction -> +5 tokens (144.6 ms) cpos=113
|
| 107 |
+
[margins] 6.77 1.35 2.63 1.17 3.36 K=2
|
| 108 |
+
verify 37: accepted 1/1 (K=2) + correction -> +2 tokens (101.7 ms) cpos=115
|
| 109 |
+
[margins] 4.15 3.02 7.74 3.32 0.44 K=5
|
| 110 |
+
verify 38: accepted 4/4 (K=5) + correction -> +5 tokens (150.5 ms) cpos=120
|
| 111 |
+
[margins] 6.82 0.76 1.23 1.03 0.54 K=2
|
| 112 |
+
verify 39: accepted 1/1 (K=2) + correction -> +2 tokens (102.6 ms) cpos=122
|
| 113 |
+
[margins] 5.52 4.28 4.81 4.73 1.83 K=6
|
| 114 |
+
verify 40: accepted 4/5 (K=6) + correction -> +5 tokens (184.2 ms) cpos=127
|
| 115 |
+
[margins] 6.72 1.42 0.76 1.72 2.71 K=2
|
| 116 |
+
verify 41: accepted 1/1 (K=2) + correction -> +2 tokens (120.3 ms) cpos=129
|
| 117 |
+
[margins] 8.22 4.18 7.00 1.69 2.13 K=6
|
| 118 |
+
verify 42: accepted 4/5 (K=6) + correction -> +5 tokens (161.5 ms) cpos=134
|
| 119 |
+
[margins] 5.38 1.44 0.07 2.37 0.06 K=2
|
| 120 |
+
verify 43: accepted 1/1 (K=2) + correction -> +2 tokens (108.3 ms) cpos=136
|
| 121 |
+
[margins] 7.92 5.49 6.24 2.92 0.99 K=5
|
| 122 |
+
verify 44: accepted 4/4 (K=5) + correction -> +5 tokens (145.8 ms) cpos=141
|
| 123 |
+
[margins] 5.74 4.75 4.48 2.38 0.42 K=5
|
| 124 |
+
verify 45: accepted 3/4 (K=5) + correction -> +4 tokens (142.9 ms) cpos=145
|
| 125 |
+
[margins] 5.11 5.49 6.65 2.11 0.19 K=5
|
| 126 |
+
verify 46: accepted 4/4 (K=5) + correction -> +5 tokens (144.6 ms) cpos=150
|
| 127 |
+
[margins] 6.12 0.87 3.19 1.04 4.85 K=2
|
| 128 |
+
verify 47: accepted 1/1 (K=2) + correction -> +2 tokens (106.8 ms) cpos=152
|
| 129 |
+
[margins] 16.85 2.26 7.90 6.93 9.32 K=6
|
| 130 |
+
verify 48: accepted 1/5 (K=6) + correction -> +2 tokens (162.6 ms) cpos=154
|
| 131 |
+
[margins] 4.67 9.58 5.65 5.67 3.12 K=6
|
| 132 |
+
verify 49: accepted 4/5 (K=6) + correction -> +5 tokens (167.4 ms) cpos=159
|
| 133 |
+
[margins] 3.89 0.43 3.22 2.06 1.95 K=2
|
| 134 |
+
verify 50: accepted 1/1 (K=2) + correction -> +2 tokens (105.8 ms) cpos=161
|
| 135 |
+
[margins] 8.80 6.55 8.25 6.20 3.80 K=6
|
| 136 |
+
verify 51: accepted 5/5 (K=6) + correction -> +6 tokens (164.3 ms) cpos=167
|
| 137 |
+
[margins] 5.39 1.13 3.65 2.62 0.45 K=2
|
| 138 |
+
verify 52: accepted 1/1 (K=2) + correction -> +2 tokens (105.2 ms) cpos=169
|
| 139 |
+
[margins] 2.83 5.73 2.60 3.78 1.87 K=6
|
| 140 |
+
verify 53: accepted 4/5 (K=6) + correction -> +5 tokens (161.4 ms) cpos=174
|
| 141 |
+
[margins] 3.37 1.79 4.23 1.81 3.44 K=6
|
| 142 |
+
verify 54: accepted 1/5 (K=6) + correction -> +2 tokens (169.3 ms) cpos=176
|
| 143 |
+
[margins] 4.20 4.83 6.29 3.31 0.32 K=5
|
| 144 |
+
verify 55: accepted 4/4 (K=5) + correction -> +5 tokens (145.1 ms) cpos=181
|
| 145 |
+
[margins] 5.92 1.45 2.38 3.10 4.02 K=2
|
| 146 |
+
verify 56: accepted 1/1 (K=2) + correction -> +2 tokens (103.2 ms) cpos=183
|
| 147 |
+
[margins] 4.30 5.57 7.92 3.28 1.12 K=5
|
| 148 |
+
verify 57: accepted 4/4 (K=5) + correction -> +5 tokens (151.3 ms) cpos=188
|
| 149 |
+
[margins] 2.80 0.59 1.67 0.90 3.63 K=2
|
| 150 |
+
verify 58: accepted 1/1 (K=2) + correction -> +2 tokens (103.4 ms) cpos=190
|
| 151 |
+
[margins] 9.57 2.20 1.58 1.82 3.21 K=6
|
| 152 |
+
verify 59: accepted 1/5 (K=6) + correction -> +2 tokens (169.3 ms) cpos=192
|
| 153 |
+
[margins] 5.06 3.22 6.36 3.78 8.67 K=6
|
| 154 |
+
verify 60: accepted 5/5 (K=6) + correction -> +6 tokens (163.0 ms) cpos=198
|
| 155 |
+
[margins] 1.71 5.56 0.84 1.93 3.82 K=3
|
| 156 |
+
verify 61: accepted 2/2 (K=3) + correction -> +3 tokens (120.2 ms) cpos=201
|
| 157 |
+
[margins] 5.64 9.06 7.78 7.19 2.60 K=6
|
| 158 |
+
verify 62: accepted 5/5 (K=6) + correction -> +6 tokens (160.8 ms) cpos=207
|
| 159 |
+
|
| 160 |
+
[spec] generated 202 tokens over 62 verifies: mean tokens/verify = 3.26 (block=5, max 6)
|
| 161 |
+
[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
|
| 162 |
+
[spec] LOSSLESS GATE: first 8 tokens match base AR -> PASS
|
| 163 |
+
[spec] SPEC-DECODE: 39.5 ms/tok = 25.35 tok/s (vs base M=1 68.6 ms/tok = 14.57 tok/s -> 1.74x)
|
| 164 |
+
[decode] PREFILL: 34 positions in 603.7 ms = 56.3 tok/s (17.756 ms/tok)
|
| 165 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=1 s=35)...
|
| 166 |
+
[margins] 1.59 0.48 1.18 1.52 0.35 K=2
|
| 167 |
+
verify 1: accepted 0/1 (K=2) + correction -> +1 tokens (104.4 ms) cpos=35
|
| 168 |
+
[margins] 2.65 2.17 1.61 2.02 4.56 K=6
|
| 169 |
+
verify 2: accepted 0/5 (K=6) + correction -> +1 tokens (159.0 ms) cpos=36
|
| 170 |
+
[margins] 1.24 1.24 0.61 3.51 0.99 K=2
|
| 171 |
+
verify 3: accepted 0/1 (K=2) + correction -> +1 tokens (96.4 ms) cpos=37
|
| 172 |
+
[margins] 1.29 2.86 1.95 1.44 0.68 K=4
|
| 173 |
+
verify 4: accepted 2/3 (K=4) + correction -> +3 tokens (123.7 ms) cpos=40
|
| 174 |
+
[margins] 1.13 0.44 0.21 0.56 1.08 K=2
|
| 175 |
+
verify 5: accepted 0/1 (K=2) + correction -> +1 tokens (97.4 ms) cpos=41
|
| 176 |
+
[margins] 1.43 4.00 0.03 0.04 0.35 K=3
|
| 177 |
+
verify 6: accepted 2/2 (K=3) + correction -> +3 tokens (112.6 ms) cpos=44
|
| 178 |
+
[margins] 0.38 5.11 10.01 2.18 0.88 K=5
|
| 179 |
+
verify 7: accepted 4/4 (K=5) + correction -> +5 tokens (138.8 ms) cpos=49
|
| 180 |
+
[margins] 5.80 2.89 0.82 1.82 1.12 K=3
|
| 181 |
+
verify 8: accepted 2/2 (K=3) + correction -> +3 tokens (111.0 ms) cpos=52
|
| 182 |
+
[margins] 4.21 5.44 7.06 2.04 1.01 K=5
|
| 183 |
+
verify 9: accepted 3/4 (K=5) + correction -> +4 tokens (141.5 ms) cpos=56
|
| 184 |
+
[margins] 3.16 3.04 1.01 0.31 2.97 K=3
|
| 185 |
+
verify 10: accepted 2/2 (K=3) + correction -> +3 tokens (109.3 ms) cpos=59
|
| 186 |
+
[margins] 0.68 0.73 2.77 0.03 4.87 K=2
|
| 187 |
+
verify 11: accepted 0/1 (K=2) + correction -> +1 tokens (102.5 ms) cpos=60
|
| 188 |
+
[margins] 1.46 1.71 5.32 3.85 1.62 K=6
|
| 189 |
+
verify 12: accepted 0/5 (K=6) + correction -> +1 tokens (150.3 ms) cpos=61
|
| 190 |
+
[margins] 0.78 2.36 2.07 1.66 0.58 K=5
|
| 191 |
+
verify 13: accepted 1/4 (K=5) + correction -> +2 tokens (134.2 ms) cpos=63
|
| 192 |
+
[margins] 2.09 3.51 1.26 4.56 0.27 K=3
|
| 193 |
+
verify 14: accepted 0/2 (K=3) + correction -> +1 tokens (115.7 ms) cpos=64
|
| 194 |
+
[margins] 3.41 0.07 0.79 5.95 0.54 K=2
|
| 195 |
+
verify 15: accepted 1/1 (K=2) + correction -> +2 tokens (98.2 ms) cpos=66
|
| 196 |
+
[margins] 1.06 0.40 3.37 4.80 0.30 K=2
|
| 197 |
+
verify 16: accepted 1/1 (K=2) + correction -> +2 tokens (105.3 ms) cpos=68
|
| 198 |
+
[margins] 0.05 5.82 0.14 2.35 1.47 K=3
|
| 199 |
+
verify 17: accepted 2/2 (K=3) + correction -> +3 tokens (111.9 ms) cpos=71
|
| 200 |
+
[margins] 2.33 1.44 1.39 4.93 0.30 K=2
|
| 201 |
+
verify 18: accepted 1/1 (K=2) + correction -> +2 tokens (105.5 ms) cpos=73
|
| 202 |
+
[margins] 1.27 0.27 0.29 5.23 0.94 K=2
|
| 203 |
+
verify 19: accepted 0/1 (K=2) + correction -> +1 tokens (100.2 ms) cpos=74
|
| 204 |
+
[margins] 7.12 1.68 3.62 2.19 2.73 K=6
|
| 205 |
+
verify 20: accepted 5/5 (K=6) + correction -> +6 tokens (161.5 ms) cpos=80
|
| 206 |
+
[margins] 4.88 4.98 3.98 2.09 7.74 K=6
|
| 207 |
+
verify 21: accepted 5/5 (K=6) + correction -> +6 tokens (159.6 ms) cpos=86
|
| 208 |
+
[margins] 7.79 2.73 2.54 6.35 1.13 K=5
|
| 209 |
+
verify 22: accepted 4/4 (K=5) + correction -> +5 tokens (144.0 ms) cpos=91
|
| 210 |
+
[margins] 7.09 2.31 3.04 6.96 1.21 K=5
|
| 211 |
+
verify 23: accepted 4/4 (K=5) + correction -> +5 tokens (147.9 ms) cpos=96
|
| 212 |
+
[margins] 9.53 4.55 3.51 8.86 3.82 K=6
|
| 213 |
+
verify 24: accepted 5/5 (K=6) + correction -> +6 tokens (158.7 ms) cpos=102
|
| 214 |
+
[margins] 10.30 3.61 6.80 6.55 5.60 K=6
|
| 215 |
+
verify 25: accepted 5/5 (K=6) + correction -> +6 tokens (166.6 ms) cpos=108
|
| 216 |
+
[margins] 2.94 0.20 0.69 0.52 2.12 K=2
|
| 217 |
+
verify 26: accepted 0/1 (K=2) + correction -> +1 tokens (102.4 ms) cpos=109
|
| 218 |
+
[margins] 7.92 5.86 4.55 6.39 5.68 K=6
|
| 219 |
+
verify 27: accepted 5/5 (K=6) + correction -> +6 tokens (160.2 ms) cpos=115
|
| 220 |
+
[margins] 9.32 8.53 8.10 2.64 7.84 K=6
|
| 221 |
+
verify 28: accepted 5/5 (K=6) + correction -> +6 tokens (168.1 ms) cpos=121
|
| 222 |
+
[margins] 8.24 4.04 7.47 6.80 0.10 K=5
|
| 223 |
+
verify 29: accepted 4/4 (K=5) + correction -> +5 tokens (148.0 ms) cpos=126
|
| 224 |
+
[margins] 9.45 5.91 6.34 1.75 4.61 K=6
|
| 225 |
+
verify 30: accepted 3/5 (K=6) + correction -> +4 tokens (184.6 ms) cpos=130
|
| 226 |
+
[margins] 8.59 7.45 6.34 2.82 10.02 K=6
|
| 227 |
+
verify 31: accepted 5/5 (K=6) + correction -> +6 tokens (167.2 ms) cpos=136
|
| 228 |
+
[margins] 7.57 4.48 5.77 8.67 3.23 K=6
|
| 229 |
+
verify 32: accepted 5/5 (K=6) + correction -> +6 tokens (163.1 ms) cpos=142
|
| 230 |
+
[margins] 13.77 7.00 9.49 11.53 8.32 K=6
|
| 231 |
+
verify 33: accepted 5/5 (K=6) + correction -> +6 tokens (168.7 ms) cpos=148
|
| 232 |
+
[margins] 3.30 1.13 8.10 4.56 3.59 K=2
|
| 233 |
+
verify 34: accepted 0/1 (K=2) + correction -> +1 tokens (104.0 ms) cpos=149
|
| 234 |
+
[margins] 7.32 9.81 7.85 8.27 5.18 K=6
|
| 235 |
+
verify 35: accepted 5/5 (K=6) + correction -> +6 tokens (161.1 ms) cpos=155
|
| 236 |
+
[margins] 10.89 9.00 7.57 1.94 8.16 K=6
|
| 237 |
+
verify 36: accepted 5/5 (K=6) + correction -> +6 tokens (169.1 ms) cpos=161
|
| 238 |
+
[margins] 10.87 5.60 3.64 9.12 7.38 K=6
|
| 239 |
+
verify 37: accepted 5/5 (K=6) + correction -> +6 tokens (162.3 ms) cpos=167
|
| 240 |
+
[margins] 14.03 7.11 9.17 10.62 10.26 K=6
|
| 241 |
+
verify 38: accepted 5/5 (K=6) + correction -> +6 tokens (169.5 ms) cpos=173
|
| 242 |
+
[margins] 2.54 7.74 10.88 6.19 6.10 K=6
|
| 243 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (160.9 ms) cpos=179
|
| 244 |
+
[margins] 9.04 10.55 6.98 9.57 6.02 K=6
|
| 245 |
+
verify 40: accepted 5/5 (K=6) + correction -> +6 tokens (166.8 ms) cpos=185
|
| 246 |
+
[margins] 11.62 10.61 9.52 7.65 10.56 K=6
|
| 247 |
+
verify 41: accepted 5/5 (K=6) + correction -> +6 tokens (162.5 ms) cpos=191
|
| 248 |
+
[margins] 12.67 9.39 4.60 9.97 2.02 K=6
|
| 249 |
+
verify 42: accepted 5/5 (K=6) + correction -> +6 tokens (168.0 ms) cpos=197
|
| 250 |
+
[margins] 14.98 7.51 10.44 9.94 7.57 K=6
|
| 251 |
+
verify 43: accepted 5/5 (K=6) + correction -> +6 tokens (164.3 ms) cpos=203
|
| 252 |
+
[margins] 4.09 0.55 3.41 5.00 4.06 K=2
|
| 253 |
+
verify 44: accepted 0/1 (K=2) + correction -> +1 tokens (108.9 ms) cpos=204
|
| 254 |
+
[margins] 5.86 8.56 7.55 6.81 3.27 K=6
|
| 255 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (162.2 ms) cpos=210
|
| 256 |
+
[margins] 10.71 10.00 9.00 4.92 9.59 K=6
|
| 257 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (169.7 ms) cpos=216
|
| 258 |
+
[margins] 15.51 5.79 7.34 9.90 5.21 K=6
|
| 259 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (162.6 ms) cpos=222
|
| 260 |
+
[margins] 14.50 6.66 9.66 5.71 6.84 K=6
|
| 261 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (170.3 ms) cpos=228
|
| 262 |
+
[margins] 1.05 8.42 11.61 5.91 1.40 K=5
|
| 263 |
+
verify 49: accepted 4/4 (K=5) + correction -> +5 tokens (147.8 ms) cpos=233
|
| 264 |
+
[margins] 5.88 0.42 3.84 8.93 2.47 K=2
|
| 265 |
+
verify 50: accepted 0/1 (K=2) + correction -> +1 tokens (105.0 ms) cpos=234
|
| 266 |
+
|
| 267 |
+
[spec] generated 200 tokens over 50 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: 34.8 ms/tok = 28.72 tok/s (vs base M=1 68.6 ms/tok = 14.57 tok/s -> 1.97x)
|
| 270 |
+
[decode] PREFILL: 41 positions in 695.5 ms = 59.0 tok/s (16.963 ms/tok)
|
| 271 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=2 s=42)...
|
| 272 |
+
[margins] 8.22 2.63 0.34 1.30 2.65 K=3
|
| 273 |
+
verify 1: accepted 2/2 (K=3) + correction -> +3 tokens (112.0 ms) cpos=44
|
| 274 |
+
[margins] 5.18 6.08 3.28 2.74 0.40 K=5
|
| 275 |
+
verify 2: accepted 3/4 (K=5) + correction -> +4 tokens (127.8 ms) cpos=48
|
| 276 |
+
[margins] 1.18 8.39 1.93 0.01 1.37 K=4
|
| 277 |
+
verify 3: accepted 0/3 (K=4) + correction -> +1 tokens (123.7 ms) cpos=49
|
| 278 |
+
[margins] 0.53 8.54 2.64 1.66 0.23 K=5
|
| 279 |
+
verify 4: accepted 0/4 (K=5) + correction -> +1 tokens (133.9 ms) cpos=50
|
| 280 |
+
[margins] 5.80 5.51 2.95 1.55 0.59 K=5
|
| 281 |
+
verify 5: accepted 0/4 (K=5) + correction -> +1 tokens (128.1 ms) cpos=51
|
| 282 |
+
[margins] 9.92 5.82 0.93 0.04 0.58 K=3
|
| 283 |
+
verify 6: accepted 1/2 (K=3) + correction -> +2 tokens (111.1 ms) cpos=53
|
| 284 |
+
[margins] 1.80 1.29 8.92 2.67 0.51 K=2
|
| 285 |
+
verify 7: accepted 0/1 (K=2) + correction -> +1 tokens (98.3 ms) cpos=54
|
| 286 |
+
[margins] 2.76 7.15 2.10 2.89 0.93 K=5
|
| 287 |
+
verify 8: accepted 2/4 (K=5) + correction -> +3 tokens (133.5 ms) cpos=57
|
| 288 |
+
[margins] 0.93 5.67 8.81 1.12 0.05 K=4
|
| 289 |
+
verify 9: accepted 0/3 (K=4) + correction -> +1 tokens (127.9 ms) cpos=58
|
| 290 |
+
[margins] 3.08 5.28 1.60 4.38 0.30 K=5
|
| 291 |
+
verify 10: accepted 2/4 (K=5) + correction -> +3 tokens (133.8 ms) cpos=61
|
| 292 |
+
[margins] 4.18 5.29 9.43 2.65 6.32 K=6
|
| 293 |
+
verify 11: accepted 3/5 (K=6) + correction -> +4 tokens (153.4 ms) cpos=65
|
| 294 |
+
[margins] 0.83 6.75 6.03 1.23 1.02 K=4
|
| 295 |
+
verify 12: accepted 3/3 (K=4) + correction -> +4 tokens (129.0 ms) cpos=69
|
| 296 |
+
[margins] 6.50 6.55 3.81 1.33 0.68 K=4
|
| 297 |
+
verify 13: accepted 2/3 (K=4) + correction -> +3 tokens (129.8 ms) cpos=72
|
| 298 |
+
[margins] 0.40 0.81 1.82 4.19 0.82 K=2
|
| 299 |
+
verify 14: accepted 1/1 (K=2) + correction -> +2 tokens (98.4 ms) cpos=74
|
| 300 |
+
[margins] 6.27 3.62 1.84 0.43 4.76 K=4
|
| 301 |
+
verify 15: accepted 1/3 (K=4) + correction -> +2 tokens (126.3 ms) cpos=76
|
| 302 |
+
[margins] 10.32 6.07 5.38 4.26 0.22 K=5
|
| 303 |
+
verify 16: accepted 2/4 (K=5) + correction -> +3 tokens (141.4 ms) cpos=79
|
| 304 |
+
[margins] 15.66 9.45 7.67 5.87 1.59 K=6
|
| 305 |
+
verify 17: accepted 4/5 (K=6) + correction -> +5 tokens (161.3 ms) cpos=84
|
| 306 |
+
[margins] 19.83 11.41 3.61 0.83 10.16 K=4
|
| 307 |
+
verify 18: accepted 2/3 (K=4) + correction -> +3 tokens (131.1 ms) cpos=87
|
| 308 |
+
[margins] 11.27 16.76 13.72 1.38 3.99 K=4
|
| 309 |
+
verify 19: accepted 3/3 (K=4) + correction -> +4 tokens (129.4 ms) cpos=91
|
| 310 |
+
[margins] 15.91 15.07 6.65 4.50 5.16 K=6
|
| 311 |
+
verify 20: accepted 5/5 (K=6) + correction -> +6 tokens (161.5 ms) cpos=97
|
| 312 |
+
[margins] 14.12 16.59 9.39 12.00 4.21 K=6
|
| 313 |
+
verify 21: accepted 5/5 (K=6) + correction -> +6 tokens (158.7 ms) cpos=103
|
| 314 |
+
[margins] 16.71 15.05 10.77 0.88 1.55 K=4
|
| 315 |
+
verify 22: accepted 3/3 (K=4) + correction -> +4 tokens (133.5 ms) cpos=107
|
| 316 |
+
[margins] 14.17 11.77 9.02 3.86 0.70 K=5
|
| 317 |
+
verify 23: accepted 4/4 (K=5) + correction -> +5 tokens (145.8 ms) cpos=112
|
| 318 |
+
[margins] 12.61 8.18 4.79 4.00 0.12 K=5
|
| 319 |
+
verify 24: accepted 2/4 (K=5) + correction -> +3 tokens (143.9 ms) cpos=115
|
| 320 |
+
[margins] 12.37 8.93 10.27 1.41 0.17 K=4
|
| 321 |
+
verify 25: accepted 3/3 (K=4) + correction -> +4 tokens (131.3 ms) cpos=119
|
| 322 |
+
[margins] 5.83 10.85 5.17 4.20 0.96 K=5
|
| 323 |
+
verify 26: accepted 4/4 (K=5) + correction -> +5 tokens (149.3 ms) cpos=124
|
| 324 |
+
[margins] 12.49 12.62 10.44 3.47 0.05 K=5
|
| 325 |
+
verify 27: accepted 4/4 (K=5) + correction -> +5 tokens (157.9 ms) cpos=129
|
| 326 |
+
[margins] 9.96 5.99 10.21 7.86 1.92 K=6
|
| 327 |
+
verify 28: accepted 5/5 (K=6) + correction -> +6 tokens (162.5 ms) cpos=135
|
| 328 |
+
[margins] 16.55 9.48 0.41 5.15 3.59 K=3
|
| 329 |
+
verify 29: accepted 2/2 (K=3) + correction -> +3 tokens (120.2 ms) cpos=138
|
| 330 |
+
[margins] 15.92 7.64 11.74 7.01 2.08 K=6
|
| 331 |
+
verify 30: accepted 4/5 (K=6) + correction -> +5 tokens (166.0 ms) cpos=143
|
| 332 |
+
[margins] 18.00 11.27 8.93 3.38 1.73 K=6
|
| 333 |
+
verify 31: accepted 5/5 (K=6) + correction -> +6 tokens (166.3 ms) cpos=149
|
| 334 |
+
[margins] 12.47 8.98 5.64 0.60 0.53 K=4
|
| 335 |
+
verify 32: accepted 3/3 (K=4) + correction -> +4 tokens (134.0 ms) cpos=153
|
| 336 |
+
[margins] 3.59 10.19 11.00 6.62 5.69 K=6
|
| 337 |
+
verify 33: accepted 4/5 (K=6) + correction -> +5 tokens (161.1 ms) cpos=158
|
| 338 |
+
[margins] 11.96 7.92 9.76 0.15 0.03 K=4
|
| 339 |
+
verify 34: accepted 3/3 (K=4) + correction -> +4 tokens (129.6 ms) cpos=162
|
| 340 |
+
[margins] 14.74 1.44 3.39 4.43 0.59 K=2
|
| 341 |
+
verify 35: accepted 1/1 (K=2) + correction -> +2 tokens (103.6 ms) cpos=164
|
| 342 |
+
[margins] 14.51 9.26 2.88 1.42 1.27 K=4
|
| 343 |
+
verify 36: accepted 2/3 (K=4) + correction -> +3 tokens (133.1 ms) cpos=167
|
| 344 |
+
[margins] 9.72 13.55 13.45 5.82 2.61 K=6
|
| 345 |
+
verify 37: accepted 4/5 (K=6) + correction -> +5 tokens (165.8 ms) cpos=172
|
| 346 |
+
[margins] 16.55 9.27 13.78 7.45 0.74 K=5
|
| 347 |
+
verify 38: accepted 4/4 (K=5) + correction -> +5 tokens (145.5 ms) cpos=177
|
| 348 |
+
[margins] 12.22 15.29 14.33 6.57 3.21 K=6
|
| 349 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (160.4 ms) cpos=183
|
| 350 |
+
[margins] 14.43 15.48 9.60 1.62 7.58 K=6
|
| 351 |
+
verify 40: accepted 5/5 (K=6) + correction -> +6 tokens (167.5 ms) cpos=189
|
| 352 |
+
[margins] 20.15 10.37 0.66 11.93 5.61 K=3
|
| 353 |
+
verify 41: accepted 2/2 (K=3) + correction -> +3 tokens (119.2 ms) cpos=192
|
| 354 |
+
[margins] 12.67 8.69 9.34 5.55 2.56 K=6
|
| 355 |
+
verify 42: accepted 5/5 (K=6) + correction -> +6 tokens (163.3 ms) cpos=198
|
| 356 |
+
[margins] 13.45 14.22 8.64 1.15 2.59 K=4
|
| 357 |
+
verify 43: accepted 3/3 (K=4) + correction -> +4 tokens (135.2 ms) cpos=202
|
| 358 |
+
[margins] 14.45 13.55 14.15 6.37 1.53 K=6
|
| 359 |
+
verify 44: accepted 4/5 (K=6) + correction -> +5 tokens (169.6 ms) cpos=207
|
| 360 |
+
[margins] 11.84 8.39 7.54 4.39 4.87 K=6
|
| 361 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (162.3 ms) cpos=213
|
| 362 |
+
[margins] 21.74 11.92 7.40 15.82 5.08 K=6
|
| 363 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (159.9 ms) cpos=219
|
| 364 |
+
[margins] 20.59 9.04 23.31 5.33 18.86 K=6
|
| 365 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (171.0 ms) cpos=225
|
| 366 |
+
[margins] 8.40 26.83 8.00 18.73 8.92 K=6
|
| 367 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (163.6 ms) cpos=231
|
| 368 |
+
[margins] 29.37 10.62 15.21 2.19 9.40 K=6
|
| 369 |
+
verify 49: accepted 5/5 (K=6) + correction -> +6 tokens (170.4 ms) cpos=237
|
| 370 |
+
[margins] 11.65 14.80 7.33 1.75 9.92 K=6
|
| 371 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (164.1 ms) cpos=243
|
| 372 |
+
|
| 373 |
+
[spec] generated 202 tokens over 50 verifies: mean tokens/verify = 4.04 (block=5, max 6)
|
| 374 |
+
[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
|
| 375 |
+
[spec] SPEC-DECODE: 35.1 ms/tok = 28.45 tok/s (vs base M=1 68.6 ms/tok = 14.57 tok/s -> 1.95x)
|
| 376 |
+
[decode] PREFILL: 26 positions in 455.1 ms = 57.1 tok/s (17.503 ms/tok)
|
| 377 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=3 s=27)...
|
| 378 |
+
[margins] 1.48 4.67 1.34 0.92 0.66 K=3
|
| 379 |
+
verify 1: accepted 1/2 (K=3) + correction -> +2 tokens (115.3 ms) cpos=28
|
| 380 |
+
[margins] 5.28 0.64 0.42 0.42 0.36 K=2
|
| 381 |
+
verify 2: accepted 1/1 (K=2) + correction -> +2 tokens (100.2 ms) cpos=30
|
| 382 |
+
[margins] 4.37 0.37 0.82 0.80 6.65 K=2
|
| 383 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (103.5 ms) cpos=32
|
| 384 |
+
[margins] 3.74 1.34 2.58 0.18 1.50 K=2
|
| 385 |
+
verify 4: accepted 1/1 (K=2) + correction -> +2 tokens (98.8 ms) cpos=34
|
| 386 |
+
[margins] 4.66 2.96 1.29 1.07 0.41 K=3
|
| 387 |
+
verify 5: accepted 2/2 (K=3) + correction -> +3 tokens (110.5 ms) cpos=37
|
| 388 |
+
[margins] 4.70 7.23 5.68 1.81 0.32 K=5
|
| 389 |
+
verify 6: accepted 4/4 (K=5) + correction -> +5 tokens (129.1 ms) cpos=42
|
| 390 |
+
[margins] 1.74 8.87 1.87 4.32 1.29 K=5
|
| 391 |
+
verify 7: accepted 4/4 (K=5) + correction -> +5 tokens (128.9 ms) cpos=47
|
| 392 |
+
[margins] 6.95 5.51 8.57 1.42 4.51 K=4
|
| 393 |
+
verify 8: accepted 3/3 (K=4) + correction -> +4 tokens (120.6 ms) cpos=51
|
| 394 |
+
[margins] 6.71 4.14 8.97 1.53 4.32 K=6
|
| 395 |
+
verify 9: accepted 5/5 (K=6) + correction -> +6 tokens (151.2 ms) cpos=57
|
| 396 |
+
[margins] 7.84 5.56 8.66 1.41 4.57 K=4
|
| 397 |
+
verify 10: accepted 3/3 (K=4) + correction -> +4 tokens (121.3 ms) cpos=61
|
| 398 |
+
[margins] 7.09 3.00 8.23 1.46 5.19 K=4
|
| 399 |
+
verify 11: accepted 3/3 (K=4) + correction -> +4 tokens (120.6 ms) cpos=65
|
| 400 |
+
[margins] 6.68 4.67 8.26 1.18 4.55 K=4
|
| 401 |
+
verify 12: accepted 3/3 (K=4) + correction -> +4 tokens (119.9 ms) cpos=69
|
| 402 |
+
[margins] 7.60 2.78 8.19 1.39 4.99 K=4
|
| 403 |
+
verify 13: accepted 3/3 (K=4) + correction -> +4 tokens (120.6 ms) cpos=73
|
| 404 |
+
[margins] 7.90 1.72 7.82 2.60 5.58 K=6
|
| 405 |
+
verify 14: accepted 1/5 (K=6) + correction -> +2 tokens (147.4 ms) cpos=75
|
| 406 |
+
[margins] 9.23 0.45 0.67 4.80 1.69 K=2
|
| 407 |
+
verify 15: accepted 0/1 (K=2) + correction -> +1 tokens (102.0 ms) cpos=76
|
| 408 |
+
[margins] 1.39 4.11 0.82 0.58 0.15 K=3
|
| 409 |
+
verify 16: accepted 0/2 (K=3) + correction -> +1 tokens (110.9 ms) cpos=77
|
| 410 |
+
[margins] 2.31 0.86 2.14 1.33 1.36 K=2
|
| 411 |
+
verify 17: accepted 0/1 (K=2) + correction -> +1 tokens (98.5 ms) cpos=78
|
| 412 |
+
[margins] 1.54 3.03 3.24 2.93 2.04 K=6
|
| 413 |
+
verify 18: accepted 2/5 (K=6) + correction -> +3 tokens (160.6 ms) cpos=81
|
| 414 |
+
[margins] 2.59 0.68 0.04 1.67 1.40 K=2
|
| 415 |
+
verify 19: accepted 1/1 (K=2) + correction -> +2 tokens (97.8 ms) cpos=83
|
| 416 |
+
[margins] 0.51 0.57 0.60 0.47 0.43 K=2
|
| 417 |
+
verify 20: accepted 1/1 (K=2) + correction -> +2 tokens (101.4 ms) cpos=85
|
| 418 |
+
[margins] 5.35 1.94 0.58 0.99 1.56 K=3
|
| 419 |
+
verify 21: accepted 1/2 (K=3) + correction -> +2 tokens (112.7 ms) cpos=87
|
| 420 |
+
[margins] 4.34 3.29 0.97 3.35 0.71 K=3
|
| 421 |
+
verify 22: accepted 1/2 (K=3) + correction -> +2 tokens (116.0 ms) cpos=89
|
| 422 |
+
[margins] 0.74 2.83 0.40 1.13 0.09 K=3
|
| 423 |
+
verify 23: accepted 2/2 (K=3) + correction -> +3 tokens (114.2 ms) cpos=92
|
| 424 |
+
[margins] 4.53 1.56 0.18 2.32 2.59 K=3
|
| 425 |
+
verify 24: accepted 2/2 (K=3) + correction -> +3 tokens (111.1 ms) cpos=95
|
| 426 |
+
[margins] 7.04 0.54 3.45 1.82 1.80 K=2
|
| 427 |
+
verify 25: accepted 1/1 (K=2) + correction -> +2 tokens (102.4 ms) cpos=97
|
| 428 |
+
[margins] 3.18 2.49 0.52 3.20 1.20 K=3
|
| 429 |
+
verify 26: accepted 2/2 (K=3) + correction -> +3 tokens (117.8 ms) cpos=100
|
| 430 |
+
[margins] 0.10 1.82 1.51 0.80 1.98 K=4
|
| 431 |
+
verify 27: accepted 1/3 (K=4) + correction -> +2 tokens (128.3 ms) cpos=102
|
| 432 |
+
[margins] 0.51 0.84 0.75 3.34 7.21 K=2
|
| 433 |
+
verify 28: accepted 0/1 (K=2) + correction -> +1 tokens (102.4 ms) cpos=103
|
| 434 |
+
[margins] 6.52 6.34 0.99 3.69 7.39 K=3
|
| 435 |
+
verify 29: accepted 2/2 (K=3) + correction -> +3 tokens (112.6 ms) cpos=106
|
| 436 |
+
[margins] 7.87 5.76 1.14 4.40 2.20 K=3
|
| 437 |
+
verify 30: accepted 2/2 (K=3) + correction -> +3 tokens (114.0 ms) cpos=109
|
| 438 |
+
[margins] 9.39 1.82 1.85 1.33 1.89 K=4
|
| 439 |
+
verify 31: accepted 3/3 (K=4) + correction -> +4 tokens (129.1 ms) cpos=113
|
| 440 |
+
[margins] 0.71 3.44 2.32 2.12 3.54 K=6
|
| 441 |
+
verify 32: accepted 0/5 (K=6) + correction -> +1 tokens (156.3 ms) cpos=114
|
| 442 |
+
[margins] 0.03 9.06 1.76 3.99 2.83 K=6
|
| 443 |
+
verify 33: accepted 2/5 (K=6) + correction -> +3 tokens (162.1 ms) cpos=117
|
| 444 |
+
[margins] 1.43 5.68 2.98 3.61 8.69 K=6
|
| 445 |
+
verify 34: accepted 5/5 (K=6) + correction -> +6 tokens (161.6 ms) cpos=123
|
| 446 |
+
[margins] 10.31 12.19 4.68 12.29 5.24 K=6
|
| 447 |
+
verify 35: accepted 5/5 (K=6) + correction -> +6 tokens (178.0 ms) cpos=129
|
| 448 |
+
[margins] 11.92 11.45 12.60 10.78 2.81 K=6
|
| 449 |
+
verify 36: accepted 5/5 (K=6) + correction -> +6 tokens (160.2 ms) cpos=135
|
| 450 |
+
[margins] 3.17 0.88 0.55 0.00 1.50 K=2
|
| 451 |
+
verify 37: accepted 1/1 (K=2) + correction -> +2 tokens (107.6 ms) cpos=137
|
| 452 |
+
[margins] 1.00 3.34 1.20 0.60 0.15 K=3
|
| 453 |
+
verify 38: accepted 0/2 (K=3) + correction -> +1 tokens (116.3 ms) cpos=138
|
| 454 |
+
[margins] 0.09 1.30 0.77 0.50 0.06 K=2
|
| 455 |
+
verify 39: accepted 1/1 (K=2) + correction -> +2 tokens (104.1 ms) cpos=140
|
| 456 |
+
[margins] 3.95 1.59 0.59 2.01 2.45 K=3
|
| 457 |
+
verify 40: accepted 0/2 (K=3) + correction -> +1 tokens (113.0 ms) cpos=141
|
| 458 |
+
[margins] 1.76 0.19 2.99 0.68 1.56 K=2
|
| 459 |
+
verify 41: accepted 1/1 (K=2) + correction -> +2 tokens (100.0 ms) cpos=143
|
| 460 |
+
[margins] 0.20 0.12 0.76 0.69 0.37 K=2
|
| 461 |
+
verify 42: accepted 0/1 (K=2) + correction -> +1 tokens (104.8 ms) cpos=144
|
| 462 |
+
[margins] 1.48 3.67 1.67 2.82 0.37 K=5
|
| 463 |
+
verify 43: accepted 1/4 (K=5) + correction -> +2 tokens (141.9 ms) cpos=146
|
| 464 |
+
[margins] 5.60 0.54 0.83 0.56 0.54 K=2
|
| 465 |
+
verify 44: accepted 1/1 (K=2) + correction -> +2 tokens (104.1 ms) cpos=148
|
| 466 |
+
[margins] 0.89 0.22 0.10 2.79 1.69 K=2
|
| 467 |
+
verify 45: accepted 1/1 (K=2) + correction -> +2 tokens (99.8 ms) cpos=150
|
| 468 |
+
[margins] 1.50 0.51 0.93 0.73 1.27 K=2
|
| 469 |
+
verify 46: accepted 1/1 (K=2) + correction -> +2 tokens (103.1 ms) cpos=152
|
| 470 |
+
[margins] 3.66 0.10 1.36 2.19 1.17 K=2
|
| 471 |
+
verify 47: accepted 1/1 (K=2) + correction -> +2 tokens (99.7 ms) cpos=154
|
| 472 |
+
[margins] 0.60 2.28 3.00 0.18 0.39 K=4
|
| 473 |
+
verify 48: accepted 1/3 (K=4) + correction -> +2 tokens (129.9 ms) cpos=156
|
| 474 |
+
[margins] 5.71 2.16 0.50 0.90 0.06 K=3
|
| 475 |
+
verify 49: accepted 1/2 (K=3) + correction -> +2 tokens (111.2 ms) cpos=158
|
| 476 |
+
[margins] 3.47 2.34 1.39 0.96 0.96 K=3
|
| 477 |
+
verify 50: accepted 2/2 (K=3) + correction -> +3 tokens (118.8 ms) cpos=161
|
| 478 |
+
[margins] 8.51 3.33 2.63 1.10 0.99 K=4
|
| 479 |
+
verify 51: accepted 1/3 (K=4) + correction -> +2 tokens (128.2 ms) cpos=163
|
| 480 |
+
[margins] 1.81 0.77 0.15 1.68 1.83 K=2
|
| 481 |
+
verify 52: accepted 1/1 (K=2) + correction -> +2 tokens (103.2 ms) cpos=165
|
| 482 |
+
[margins] 3.12 3.98 2.16 2.02 2.93 K=6
|
| 483 |
+
verify 53: accepted 2/5 (K=6) + correction -> +3 tokens (157.7 ms) cpos=168
|
| 484 |
+
[margins] 4.96 1.61 6.24 2.24 0.05 K=5
|
| 485 |
+
verify 54: accepted 4/4 (K=5) + correction -> +5 tokens (144.8 ms) cpos=173
|
| 486 |
+
[margins] 0.19 7.13 0.59 0.17 0.25 K=3
|
| 487 |
+
verify 55: accepted 0/2 (K=3) + correction -> +1 tokens (116.6 ms) cpos=174
|
| 488 |
+
[margins] 0.09 0.21 3.36 0.47 4.10 K=2
|
| 489 |
+
verify 56: accepted 0/1 (K=2) + correction -> +1 tokens (104.9 ms) cpos=175
|
| 490 |
+
[margins] 0.12 0.96 3.10 0.45 1.62 K=2
|
| 491 |
+
verify 57: accepted 1/1 (K=2) + correction -> +2 tokens (107.3 ms) cpos=177
|
| 492 |
+
[margins] 3.01 3.26 3.16 1.47 2.84 K=4
|
| 493 |
+
verify 58: accepted 2/3 (K=4) + correction -> +3 tokens (128.5 ms) cpos=180
|
| 494 |
+
[margins] 0.81 0.23 0.71 1.46 0.79 K=2
|
| 495 |
+
verify 59: accepted 0/1 (K=2) + correction -> +1 tokens (100.5 ms) cpos=181
|
| 496 |
+
[margins] 5.66 0.40 0.02 3.27 7.62 K=2
|
| 497 |
+
verify 60: accepted 1/1 (K=2) + correction -> +2 tokens (100.6 ms) cpos=183
|
| 498 |
+
[margins] 3.42 4.08 5.21 3.40 1.90 K=6
|
| 499 |
+
verify 61: accepted 2/5 (K=6) + correction -> +3 tokens (160.9 ms) cpos=186
|
| 500 |
+
[margins] 3.22 2.73 0.78 0.78 0.79 K=3
|
| 501 |
+
verify 62: accepted 2/2 (K=3) + correction -> +3 tokens (118.1 ms) cpos=189
|
| 502 |
+
[margins] 4.45 1.61 0.96 0.71 0.21 K=3
|
| 503 |
+
verify 63: accepted 2/2 (K=3) + correction -> +3 tokens (120.1 ms) cpos=192
|
| 504 |
+
[margins] 5.56 0.89 0.02 0.55 0.88 K=2
|
| 505 |
+
verify 64: accepted 1/1 (K=2) + correction -> +2 tokens (100.8 ms) cpos=194
|
| 506 |
+
[margins] 0.15 0.60 2.98 1.84 0.14 K=2
|
| 507 |
+
verify 65: accepted 0/1 (K=2) + correction -> +1 tokens (106.0 ms) cpos=195
|
| 508 |
+
[margins] 2.55 0.52 1.33 4.17 0.70 K=2
|
| 509 |
+
verify 66: accepted 1/1 (K=2) + correction -> +2 tokens (105.3 ms) cpos=197
|
| 510 |
+
[margins] 0.60 1.75 6.71 0.55 3.24 K=4
|
| 511 |
+
verify 67: accepted 0/3 (K=4) + correction -> +1 tokens (130.5 ms) cpos=198
|
| 512 |
+
[margins] 2.72 0.86 1.49 4.63 0.86 K=2
|
| 513 |
+
verify 68: accepted 0/1 (K=2) + correction -> +1 tokens (106.3 ms) cpos=199
|
| 514 |
+
[margins] 5.05 8.27 7.55 2.19 5.42 K=6
|
| 515 |
+
verify 69: accepted 0/5 (K=6) + correction -> +1 tokens (166.4 ms) cpos=200
|
| 516 |
+
[margins] 8.66 6.20 0.27 3.78 2.16 K=3
|
| 517 |
+
verify 70: accepted 2/2 (K=3) + correction -> +3 tokens (112.8 ms) cpos=203
|
| 518 |
+
[margins] 4.11 4.18 2.15 1.22 0.60 K=4
|
| 519 |
+
verify 71: accepted 1/3 (K=4) + correction -> +2 tokens (128.2 ms) cpos=205
|
| 520 |
+
[margins] 1.59 0.62 0.11 0.97 2.01 K=2
|
| 521 |
+
verify 72: accepted 1/1 (K=2) + correction -> +2 tokens (100.4 ms) cpos=207
|
| 522 |
+
[margins] 0.50 1.37 0.65 3.45 2.94 K=2
|
| 523 |
+
verify 73: accepted 0/1 (K=2) + correction -> +1 tokens (104.3 ms) cpos=208
|
| 524 |
+
[margins] 10.96 1.27 1.43 4.93 1.36 K=2
|
| 525 |
+
verify 74: accepted 1/1 (K=2) + correction -> +2 tokens (101.5 ms) cpos=210
|
| 526 |
+
[margins] 2.46 2.68 0.96 0.77 3.83 K=3
|
| 527 |
+
verify 75: accepted 2/2 (K=3) + correction -> +3 tokens (119.6 ms) cpos=213
|
| 528 |
+
[margins] 1.26 0.13 0.11 1.21 0.36 K=2
|
| 529 |
+
verify 76: accepted 1/1 (K=2) + correction -> +2 tokens (99.3 ms) cpos=215
|
| 530 |
+
[margins] 3.45 3.22 7.61 5.54 0.22 K=5
|
| 531 |
+
verify 77: accepted 4/4 (K=5) + correction -> +5 tokens (150.1 ms) cpos=220
|
| 532 |
+
[margins] 3.92 2.51 2.97 0.15 3.78 K=4
|
| 533 |
+
verify 78: accepted 0/3 (K=4) + correction -> +1 tokens (133.9 ms) cpos=221
|
| 534 |
+
[margins] 11.65 2.78 2.67 1.08 4.60 K=4
|
| 535 |
+
verify 79: accepted 3/3 (K=4) + correction -> +4 tokens (131.5 ms) cpos=225
|
| 536 |
+
[margins] 12.17 4.09 0.34 1.69 0.33 K=3
|
| 537 |
+
verify 80: accepted 2/2 (K=3) + correction -> +3 tokens (122.6 ms) cpos=228
|
| 538 |
+
|
| 539 |
+
[spec] generated 202 tokens over 80 verifies: mean tokens/verify = 2.52 (block=5, max 6)
|
| 540 |
+
[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
|
| 541 |
+
[spec] SPEC-DECODE: 47.4 ms/tok = 21.08 tok/s (vs base M=1 68.6 ms/tok = 14.57 tok/s -> 1.45x)
|
| 542 |
+
[decode] PREFILL: 14 positions in 284.9 ms = 49.1 tok/s (20.348 ms/tok)
|
| 543 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=4 s=15)...
|
| 544 |
+
[margins] 0.01 8.63 2.90 3.16 2.74 K=6
|
| 545 |
+
verify 1: accepted 0/5 (K=6) + correction -> +1 tokens (158.9 ms) cpos=15
|
| 546 |
+
[margins] 0.38 1.46 0.23 0.02 0.23 K=2
|
| 547 |
+
verify 2: accepted 1/1 (K=2) + correction -> +2 tokens (101.1 ms) cpos=17
|
| 548 |
+
[margins] 0.34 0.29 0.30 1.05 0.82 K=2
|
| 549 |
+
verify 3: accepted 0/1 (K=2) + correction -> +1 tokens (96.3 ms) cpos=18
|
| 550 |
+
[margins] 0.78 0.66 0.20 0.63 0.35 K=2
|
| 551 |
+
verify 4: accepted 1/1 (K=2) + correction -> +2 tokens (99.9 ms) cpos=20
|
| 552 |
+
[margins] 0.85 0.78 0.02 0.26 0.25 K=2
|
| 553 |
+
verify 5: accepted 1/1 (K=2) + correction -> +2 tokens (95.0 ms) cpos=22
|
| 554 |
+
[margins] 2.01 1.20 0.42 0.50 1.42 K=2
|
| 555 |
+
verify 6: accepted 1/1 (K=2) + correction -> +2 tokens (101.2 ms) cpos=24
|
| 556 |
+
[margins] 0.21 1.28 0.61 0.05 3.77 K=2
|
| 557 |
+
verify 7: accepted 0/1 (K=2) + correction -> +1 tokens (96.7 ms) cpos=25
|
| 558 |
+
[margins] 0.44 0.67 0.61 0.59 0.60 K=2
|
| 559 |
+
verify 8: accepted 1/1 (K=2) + correction -> +2 tokens (96.7 ms) cpos=27
|
| 560 |
+
[margins] 0.30 0.49 0.32 0.77 1.55 K=2
|
| 561 |
+
verify 9: accepted 1/1 (K=2) + correction -> +2 tokens (104.3 ms) cpos=29
|
| 562 |
+
[margins] 3.74 1.80 0.16 2.43 0.04 K=3
|
| 563 |
+
verify 10: accepted 2/2 (K=3) + correction -> +3 tokens (113.0 ms) cpos=32
|
| 564 |
+
[margins] 0.78 0.35 0.09 0.00 1.15 K=2
|
| 565 |
+
verify 11: accepted 1/1 (K=2) + correction -> +2 tokens (95.4 ms) cpos=34
|
| 566 |
+
[margins] 1.93 1.67 1.38 1.19 0.44 K=3
|
| 567 |
+
verify 12: accepted 1/2 (K=3) + correction -> +2 tokens (110.1 ms) cpos=36
|
| 568 |
+
[margins] 0.96 0.13 1.03 1.39 1.05 K=2
|
| 569 |
+
verify 13: accepted 0/1 (K=2) + correction -> +1 tokens (96.1 ms) cpos=37
|
| 570 |
+
[margins] 0.26 2.39 0.85 0.22 0.21 K=3
|
| 571 |
+
verify 14: accepted 1/2 (K=3) + correction -> +2 tokens (113.3 ms) cpos=39
|
| 572 |
+
[margins] 3.81 1.22 0.52 0.44 1.64 K=2
|
| 573 |
+
verify 15: accepted 0/1 (K=2) + correction -> +1 tokens (99.2 ms) cpos=40
|
| 574 |
+
[margins] 3.25 3.88 0.94 2.44 1.58 K=3
|
| 575 |
+
verify 16: accepted 1/2 (K=3) + correction -> +2 tokens (110.1 ms) cpos=42
|
| 576 |
+
[margins] 0.27 0.04 0.75 0.91 0.08 K=2
|
| 577 |
+
verify 17: accepted 1/1 (K=2) + correction -> +2 tokens (101.8 ms) cpos=44
|
| 578 |
+
[margins] 1.27 7.42 0.11 1.32 1.84 K=3
|
| 579 |
+
verify 18: accepted 2/2 (K=3) + correction -> +3 tokens (110.5 ms) cpos=47
|
| 580 |
+
[margins] 3.87 7.83 2.27 0.88 2.79 K=4
|
| 581 |
+
verify 19: accepted 3/3 (K=4) + correction -> +4 tokens (125.9 ms) cpos=51
|
| 582 |
+
[margins] 2.79 0.31 0.36 0.21 2.84 K=2
|
| 583 |
+
verify 20: accepted 0/1 (K=2) + correction -> +1 tokens (102.3 ms) cpos=52
|
| 584 |
+
[margins] 2.06 1.29 1.72 1.56 3.65 K=2
|
| 585 |
+
verify 21: accepted 0/1 (K=2) + correction -> +1 tokens (98.9 ms) cpos=53
|
| 586 |
+
[margins] 8.37 3.11 1.18 0.62 2.69 K=3
|
| 587 |
+
verify 22: accepted 2/2 (K=3) + correction -> +3 tokens (117.2 ms) cpos=56
|
| 588 |
+
[margins] 5.15 1.91 3.42 3.45 0.61 K=5
|
| 589 |
+
verify 23: accepted 4/4 (K=5) + correction -> +5 tokens (137.3 ms) cpos=61
|
| 590 |
+
[margins] 0.01 1.86 0.93 3.17 1.39 K=3
|
| 591 |
+
verify 24: accepted 0/2 (K=3) + correction -> +1 tokens (114.1 ms) cpos=62
|
| 592 |
+
[margins] 1.83 1.00 1.57 1.95 2.58 K=2
|
| 593 |
+
verify 25: accepted 0/1 (K=2) + correction -> +1 tokens (100.4 ms) cpos=63
|
| 594 |
+
[margins] 1.01 1.37 1.08 0.54 0.45 K=2
|
| 595 |
+
verify 26: accepted 1/1 (K=2) + correction -> +2 tokens (102.0 ms) cpos=65
|
| 596 |
+
[margins] 0.31 2.24 0.50 0.93 1.04 K=3
|
| 597 |
+
verify 27: accepted 0/2 (K=3) + correction -> +1 tokens (113.6 ms) cpos=66
|
| 598 |
+
[margins] 0.22 4.94 0.72 0.11 0.42 K=3
|
| 599 |
+
verify 28: accepted 0/2 (K=3) + correction -> +1 tokens (114.2 ms) cpos=67
|
| 600 |
+
[margins] 1.72 0.19 0.00 0.29 2.26 K=2
|
| 601 |
+
verify 29: accepted 1/1 (K=2) + correction -> +2 tokens (104.4 ms) cpos=69
|
| 602 |
+
[margins] 0.67 2.48 0.67 1.78 0.07 K=3
|
| 603 |
+
verify 30: accepted 0/2 (K=3) + correction -> +1 tokens (115.8 ms) cpos=70
|
| 604 |
+
[margins] 1.29 1.17 0.40 0.97 0.11 K=2
|
| 605 |
+
verify 31: accepted 0/1 (K=2) + correction -> +1 tokens (102.2 ms) cpos=71
|
| 606 |
+
[margins] 0.12 0.34 0.33 0.82 1.47 K=2
|
| 607 |
+
verify 32: accepted 0/1 (K=2) + correction -> +1 tokens (103.6 ms) cpos=72
|
| 608 |
+
[margins] 0.13 0.12 1.61 0.63 0.38 K=2
|
| 609 |
+
verify 33: accepted 0/1 (K=2) + correction -> +1 tokens (98.1 ms) cpos=73
|
| 610 |
+
[margins] 7.59 1.80 1.05 0.75 0.20 K=3
|
| 611 |
+
verify 34: accepted 2/2 (K=3) + correction -> +3 tokens (113.7 ms) cpos=76
|
| 612 |
+
[margins] 0.17 0.75 2.36 0.74 1.64 K=2
|
| 613 |
+
verify 35: accepted 1/1 (K=2) + correction -> +2 tokens (97.9 ms) cpos=78
|
| 614 |
+
[margins] 0.34 0.06 2.24 0.52 9.83 K=2
|
| 615 |
+
verify 36: accepted 1/1 (K=2) + correction -> +2 tokens (104.4 ms) cpos=80
|
| 616 |
+
[margins] 1.54 4.99 2.21 2.38 9.55 K=6
|
| 617 |
+
verify 37: accepted 5/5 (K=6) + correction -> +6 tokens (163.0 ms) cpos=86
|
| 618 |
+
[margins] 7.12 8.22 4.56 4.00 2.24 K=6
|
| 619 |
+
verify 38: accepted 2/5 (K=6) + correction -> +3 tokens (151.2 ms) cpos=89
|
| 620 |
+
[margins] 9.38 5.33 2.94 1.31 0.32 K=4
|
| 621 |
+
verify 39: accepted 1/3 (K=4) + correction -> +2 tokens (123.0 ms) cpos=91
|
| 622 |
+
[margins] 7.12 4.27 2.56 0.90 1.80 K=4
|
| 623 |
+
verify 40: accepted 1/3 (K=4) + correction -> +2 tokens (122.4 ms) cpos=93
|
| 624 |
+
[margins] 5.38 0.03 3.37 0.46 0.16 K=2
|
| 625 |
+
verify 41: accepted 1/1 (K=2) + correction -> +2 tokens (101.5 ms) cpos=95
|
| 626 |
+
[margins] 5.08 2.94 2.05 1.17 4.67 K=4
|
| 627 |
+
verify 42: accepted 3/3 (K=4) + correction -> +4 tokens (122.2 ms) cpos=99
|
| 628 |
+
[margins] 3.12 6.31 2.86 2.76 2.25 K=6
|
| 629 |
+
verify 43: accepted 5/5 (K=6) + correction -> +6 tokens (153.2 ms) cpos=105
|
| 630 |
+
[margins] 2.71 8.53 2.55 5.11 2.84 K=6
|
| 631 |
+
verify 44: accepted 5/5 (K=6) + correction -> +6 tokens (148.7 ms) cpos=111
|
| 632 |
+
[margins] 2.92 9.11 2.82 4.95 3.12 K=6
|
| 633 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (154.8 ms) cpos=117
|
| 634 |
+
[margins] 3.45 8.54 2.84 4.46 2.94 K=6
|
| 635 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (151.1 ms) cpos=123
|
| 636 |
+
[margins] 3.62 8.56 2.74 5.23 2.78 K=6
|
| 637 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (170.2 ms) cpos=129
|
| 638 |
+
[margins] 3.89 9.11 2.96 5.21 2.52 K=6
|
| 639 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (151.2 ms) cpos=135
|
| 640 |
+
[margins] 3.10 9.44 1.76 4.55 2.04 K=6
|
| 641 |
+
verify 49: accepted 5/5 (K=6) + correction -> +6 tokens (155.3 ms) cpos=141
|
| 642 |
+
[margins] 4.30 9.53 3.36 4.49 3.08 K=6
|
| 643 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (151.4 ms) cpos=147
|
| 644 |
+
[margins] 4.50 9.32 2.88 4.76 2.59 K=6
|
| 645 |
+
verify 51: accepted 5/5 (K=6) + correction -> +6 tokens (157.6 ms) cpos=153
|
| 646 |
+
[margins] 2.96 10.21 1.40 6.13 2.34 K=3
|
| 647 |
+
verify 52: accepted 2/2 (K=3) + correction -> +3 tokens (118.0 ms) cpos=156
|
| 648 |
+
[margins] 6.38 1.34 5.25 1.66 2.31 K=2
|
| 649 |
+
verify 53: accepted 1/1 (K=2) + correction -> +2 tokens (100.8 ms) cpos=158
|
| 650 |
+
[margins] 4.58 0.54 0.24 0.53 0.94 K=2
|
| 651 |
+
verify 54: accepted 0/1 (K=2) + correction -> +1 tokens (104.9 ms) cpos=159
|
| 652 |
+
[margins] 8.20 0.39 0.26 0.16 1.51 K=2
|
| 653 |
+
verify 55: accepted 1/1 (K=2) + correction -> +2 tokens (105.4 ms) cpos=161
|
| 654 |
+
[margins] 9.93 3.58 1.58 4.13 2.47 K=6
|
| 655 |
+
verify 56: accepted 4/5 (K=6) + correction -> +5 tokens (157.2 ms) cpos=166
|
| 656 |
+
[margins] 2.08 3.04 4.06 0.32 1.21 K=4
|
| 657 |
+
verify 57: accepted 0/3 (K=4) + correction -> +1 tokens (132.1 ms) cpos=167
|
| 658 |
+
[margins] 9.36 4.18 7.96 7.27 4.74 K=6
|
| 659 |
+
verify 58: accepted 5/5 (K=6) + correction -> +6 tokens (166.4 ms) cpos=173
|
| 660 |
+
[margins] 6.12 0.52 0.57 2.33 0.32 K=2
|
| 661 |
+
verify 59: accepted 1/1 (K=2) + correction -> +2 tokens (99.6 ms) cpos=175
|
| 662 |
+
[margins] 6.66 7.54 4.32 1.80 3.22 K=6
|
| 663 |
+
verify 60: accepted 5/5 (K=6) + correction -> +6 tokens (167.6 ms) cpos=181
|
| 664 |
+
[margins] 11.55 10.84 2.76 2.52 4.00 K=6
|
| 665 |
+
verify 61: accepted 5/5 (K=6) + correction -> +6 tokens (163.1 ms) cpos=187
|
| 666 |
+
[margins] 20.48 6.85 3.96 3.78 3.58 K=6
|
| 667 |
+
verify 62: accepted 4/5 (K=6) + correction -> +5 tokens (169.0 ms) cpos=192
|
| 668 |
+
[margins] 7.93 7.46 1.88 8.20 9.99 K=6
|
| 669 |
+
verify 63: accepted 5/5 (K=6) + correction -> +6 tokens (162.5 ms) cpos=198
|
| 670 |
+
[margins] 13.73 13.65 6.14 3.87 10.56 K=6
|
| 671 |
+
verify 64: accepted 5/5 (K=6) + correction -> +6 tokens (170.8 ms) cpos=204
|
| 672 |
+
[margins] 22.41 8.11 5.10 7.31 6.49 K=6
|
| 673 |
+
verify 65: accepted 5/5 (K=6) + correction -> +6 tokens (159.9 ms) cpos=210
|
| 674 |
+
[margins] 13.18 12.17 16.55 10.06 9.45 K=6
|
| 675 |
+
verify 66: accepted 5/5 (K=6) + correction -> +6 tokens (167.1 ms) cpos=216
|
| 676 |
+
|
| 677 |
+
[spec] generated 202 tokens over 66 verifies: mean tokens/verify = 3.06 (block=5, max 6)
|
| 678 |
+
[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
|
| 679 |
+
[spec] SPEC-DECODE: 39.9 ms/tok = 25.04 tok/s (vs base M=1 68.6 ms/tok = 14.57 tok/s -> 1.72x)
|
| 680 |
+
[decode] PREFILL: 82 positions in 1325.3 ms = 61.9 tok/s (16.162 ms/tok)
|
| 681 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=5 s=83)...
|
| 682 |
+
[margins] 6.90 1.07 0.12 1.48 1.43 K=2
|
| 683 |
+
verify 1: accepted 1/1 (K=2) + correction -> +2 tokens (107.2 ms) cpos=84
|
| 684 |
+
[margins] 0.70 0.16 0.55 1.23 0.03 K=2
|
| 685 |
+
verify 2: accepted 0/1 (K=2) + correction -> +1 tokens (101.2 ms) cpos=85
|
| 686 |
+
[margins] 0.17 0.01 0.60 2.16 0.30 K=2
|
| 687 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (99.4 ms) cpos=87
|
| 688 |
+
[margins] 3.40 2.99 3.04 1.38 1.69 K=4
|
| 689 |
+
verify 4: accepted 3/3 (K=4) + correction -> +4 tokens (129.4 ms) cpos=91
|
| 690 |
+
[margins] 13.64 6.23 5.25 5.03 4.14 K=6
|
| 691 |
+
verify 5: accepted 5/5 (K=6) + correction -> +6 tokens (164.4 ms) cpos=97
|
| 692 |
+
[margins] 8.06 1.18 2.06 0.72 2.18 K=2
|
| 693 |
+
verify 6: accepted 1/1 (K=2) + correction -> +2 tokens (100.3 ms) cpos=99
|
| 694 |
+
[margins] 10.22 1.24 3.08 2.16 1.06 K=2
|
| 695 |
+
verify 7: accepted 1/1 (K=2) + correction -> +2 tokens (105.1 ms) cpos=101
|
| 696 |
+
[margins] 3.95 0.39 0.03 2.02 1.98 K=2
|
| 697 |
+
verify 8: accepted 1/1 (K=2) + correction -> +2 tokens (102.8 ms) cpos=103
|
| 698 |
+
[margins] 2.34 0.89 2.43 0.26 1.98 K=2
|
| 699 |
+
verify 9: accepted 1/1 (K=2) + correction -> +2 tokens (103.9 ms) cpos=105
|
| 700 |
+
[margins] 9.41 8.33 8.50 4.76 1.84 K=6
|
| 701 |
+
verify 10: accepted 5/5 (K=6) + correction -> +6 tokens (159.9 ms) cpos=111
|
| 702 |
+
[margins] 7.30 7.99 7.40 10.61 1.87 K=6
|
| 703 |
+
verify 11: accepted 4/5 (K=6) + correction -> +5 tokens (168.0 ms) cpos=116
|
| 704 |
+
[margins] 11.85 14.75 7.42 2.01 1.51 K=6
|
| 705 |
+
verify 12: accepted 5/5 (K=6) + correction -> +6 tokens (162.1 ms) cpos=122
|
| 706 |
+
[margins] 8.90 4.92 7.48 1.89 2.90 K=6
|
| 707 |
+
verify 13: accepted 3/5 (K=6) + correction -> +4 tokens (181.6 ms) cpos=126
|
| 708 |
+
[margins] 12.65 2.92 2.82 12.71 6.47 K=6
|
| 709 |
+
verify 14: accepted 5/5 (K=6) + correction -> +6 tokens (181.4 ms) cpos=132
|
| 710 |
+
[margins] 12.77 15.11 0.65 10.58 12.73 K=3
|
| 711 |
+
verify 15: accepted 2/2 (K=3) + correction -> +3 tokens (115.5 ms) cpos=135
|
| 712 |
+
[margins] 15.28 15.66 11.14 8.80 2.59 K=6
|
| 713 |
+
verify 16: accepted 4/5 (K=6) + correction -> +5 tokens (167.2 ms) cpos=140
|
| 714 |
+
[margins] 5.05 3.67 6.01 4.74 5.21 K=6
|
| 715 |
+
verify 17: accepted 0/5 (K=6) + correction -> +1 tokens (156.3 ms) cpos=141
|
| 716 |
+
[margins] 8.74 7.32 0.99 3.14 0.27 K=3
|
| 717 |
+
verify 18: accepted 2/2 (K=3) + correction -> +3 tokens (118.1 ms) cpos=144
|
| 718 |
+
[margins] 10.88 5.31 4.68 1.95 2.16 K=6
|
| 719 |
+
verify 19: accepted 4/5 (K=6) + correction -> +5 tokens (162.1 ms) cpos=149
|
| 720 |
+
[margins] 15.53 10.57 1.85 6.49 11.66 K=6
|
| 721 |
+
verify 20: accepted 5/5 (K=6) + correction -> +6 tokens (161.5 ms) cpos=155
|
| 722 |
+
[margins] 17.17 12.11 13.38 9.05 0.53 K=5
|
| 723 |
+
verify 21: accepted 4/4 (K=5) + correction -> +5 tokens (149.2 ms) cpos=160
|
| 724 |
+
[margins] 10.42 2.59 9.22 6.81 4.29 K=6
|
| 725 |
+
verify 22: accepted 0/5 (K=6) + correction -> +1 tokens (157.2 ms) cpos=161
|
| 726 |
+
[margins] 11.52 6.07 0.85 5.75 0.97 K=3
|
| 727 |
+
verify 23: accepted 2/2 (K=3) + correction -> +3 tokens (117.2 ms) cpos=164
|
| 728 |
+
[margins] 10.45 8.09 5.55 8.29 8.22 K=6
|
| 729 |
+
verify 24: accepted 5/5 (K=6) + correction -> +6 tokens (161.9 ms) cpos=170
|
| 730 |
+
[margins] 1.38 7.30 11.27 6.31 13.32 K=6
|
| 731 |
+
verify 25: accepted 0/5 (K=6) + correction -> +1 tokens (166.9 ms) cpos=171
|
| 732 |
+
[margins] 0.31 8.92 10.72 5.05 8.66 K=6
|
| 733 |
+
verify 26: accepted 3/5 (K=6) + correction -> +4 tokens (168.3 ms) cpos=175
|
| 734 |
+
[margins] 16.55 17.06 13.01 7.74 1.49 K=5
|
| 735 |
+
verify 27: accepted 4/4 (K=5) + correction -> +5 tokens (149.7 ms) cpos=180
|
| 736 |
+
[margins] 17.17 16.06 6.59 6.39 7.71 K=6
|
| 737 |
+
verify 28: accepted 5/5 (K=6) + correction -> +6 tokens (160.9 ms) cpos=186
|
| 738 |
+
[margins] 8.06 8.29 2.92 7.21 2.80 K=6
|
| 739 |
+
verify 29: accepted 5/5 (K=6) + correction -> +6 tokens (167.5 ms) cpos=192
|
| 740 |
+
[margins] 14.01 16.08 8.93 11.02 13.03 K=6
|
| 741 |
+
verify 30: accepted 5/5 (K=6) + correction -> +6 tokens (161.9 ms) cpos=198
|
| 742 |
+
[margins] 9.55 9.30 13.07 14.86 3.76 K=6
|
| 743 |
+
verify 31: accepted 5/5 (K=6) + correction -> +6 tokens (164.1 ms) cpos=204
|
| 744 |
+
[margins] 9.72 2.69 5.07 6.21 5.18 K=6
|
| 745 |
+
verify 32: accepted 5/5 (K=6) + correction -> +6 tokens (161.6 ms) cpos=210
|
| 746 |
+
[margins] 5.90 7.11 6.97 9.63 0.50 K=5
|
| 747 |
+
verify 33: accepted 4/4 (K=5) + correction -> +5 tokens (145.3 ms) cpos=215
|
| 748 |
+
[margins] 16.32 18.20 13.04 10.79 0.15 K=5
|
| 749 |
+
verify 34: accepted 4/4 (K=5) + correction -> +5 tokens (151.9 ms) cpos=220
|
| 750 |
+
[margins] 19.59 14.11 4.53 4.83 5.60 K=6
|
| 751 |
+
verify 35: accepted 5/5 (K=6) + correction -> +6 tokens (159.7 ms) cpos=226
|
| 752 |
+
[margins] 8.69 5.83 2.58 11.91 1.02 K=5
|
| 753 |
+
verify 36: accepted 4/4 (K=5) + correction -> +5 tokens (146.6 ms) cpos=231
|
| 754 |
+
[margins] 5.56 13.43 5.46 2.89 8.80 K=6
|
| 755 |
+
verify 37: accepted 3/5 (K=6) + correction -> +4 tokens (169.1 ms) cpos=235
|
| 756 |
+
[margins] 7.08 14.35 9.60 6.23 1.06 K=5
|
| 757 |
+
verify 38: accepted 4/4 (K=5) + correction -> +5 tokens (152.8 ms) cpos=240
|
| 758 |
+
[margins] 20.42 15.29 5.80 5.10 5.25 K=6
|
| 759 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (162.7 ms) cpos=246
|
| 760 |
+
[margins] 10.58 6.30 2.62 6.58 10.12 K=6
|
| 761 |
+
verify 40: accepted 2/5 (K=6) + correction -> +3 tokens (169.2 ms) cpos=249
|
| 762 |
+
[margins] 14.35 9.28 3.44 11.69 11.06 K=6
|
| 763 |
+
verify 41: accepted 5/5 (K=6) + correction -> +6 tokens (161.5 ms) cpos=255
|
| 764 |
+
[margins] 16.31 16.87 12.54 8.25 3.74 K=6
|
| 765 |
+
verify 42: accepted 5/5 (K=6) + correction -> +6 tokens (183.1 ms) cpos=261
|
| 766 |
+
[margins] 16.66 10.03 8.10 8.21 0.58 K=5
|
| 767 |
+
verify 43: accepted 4/4 (K=5) + correction -> +5 tokens (146.0 ms) cpos=266
|
| 768 |
+
[margins] 12.32 9.33 2.69 5.28 6.15 K=6
|
| 769 |
+
verify 44: accepted 2/5 (K=6) + correction -> +3 tokens (168.2 ms) cpos=269
|
| 770 |
+
[margins] 15.17 11.97 4.16 9.50 10.34 K=6
|
| 771 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (165.5 ms) cpos=275
|
| 772 |
+
[margins] 13.10 18.46 13.98 9.48 4.77 K=6
|
| 773 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (169.3 ms) cpos=281
|
| 774 |
+
[margins] 16.63 7.05 7.50 7.95 0.91 K=5
|
| 775 |
+
verify 47: accepted 4/4 (K=5) + correction -> +5 tokens (145.6 ms) cpos=286
|
| 776 |
+
|
| 777 |
+
[spec] generated 204 tokens over 47 verifies: mean tokens/verify = 4.34 (block=5, max 6)
|
| 778 |
+
[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
|
| 779 |
+
[spec] SPEC-DECODE: 34.3 ms/tok = 29.18 tok/s (vs base M=1 68.6 ms/tok = 14.57 tok/s -> 2.00x)
|
| 780 |
+
[decode] PREFILL: 14 positions in 285.8 ms = 49.0 tok/s (20.414 ms/tok)
|
| 781 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=6 s=15)...
|
| 782 |
+
[margins] 0.32 7.93 3.07 0.82 5.18 K=4
|
| 783 |
+
verify 1: accepted 0/3 (K=4) + correction -> +1 tokens (123.9 ms) cpos=15
|
| 784 |
+
[margins] 1.44 0.38 2.32 0.28 0.76 K=2
|
| 785 |
+
verify 2: accepted 0/1 (K=2) + correction -> +1 tokens (104.1 ms) cpos=16
|
| 786 |
+
[margins] 3.72 0.25 0.77 0.64 1.05 K=2
|
| 787 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (98.9 ms) cpos=18
|
| 788 |
+
[margins] 2.29 0.28 0.22 1.28 1.74 K=2
|
| 789 |
+
verify 4: accepted 1/1 (K=2) + correction -> +2 tokens (103.0 ms) cpos=20
|
| 790 |
+
[margins] 3.78 0.29 2.08 0.82 2.33 K=2
|
| 791 |
+
verify 5: accepted 1/1 (K=2) + correction -> +2 tokens (98.8 ms) cpos=22
|
| 792 |
+
[margins] 3.48 1.43 1.82 1.46 3.01 K=2
|
| 793 |
+
verify 6: accepted 1/1 (K=2) + correction -> +2 tokens (102.1 ms) cpos=24
|
| 794 |
+
[margins] 3.90 4.08 2.28 0.26 2.22 K=4
|
| 795 |
+
verify 7: accepted 3/3 (K=4) + correction -> +4 tokens (117.7 ms) cpos=28
|
| 796 |
+
[margins] 3.28 6.35 3.13 3.72 2.35 K=6
|
| 797 |
+
verify 8: accepted 2/5 (K=6) + correction -> +3 tokens (144.1 ms) cpos=31
|
| 798 |
+
[margins] 2.48 0.97 3.63 2.35 2.08 K=2
|
| 799 |
+
verify 9: accepted 0/1 (K=2) + correction -> +1 tokens (99.0 ms) cpos=32
|
| 800 |
+
[margins] 8.12 0.51 1.45 1.10 0.14 K=2
|
| 801 |
+
verify 10: accepted 1/1 (K=2) + correction -> +2 tokens (96.9 ms) cpos=34
|
| 802 |
+
[margins] 0.25 6.09 1.43 0.52 1.01 K=3
|
| 803 |
+
verify 11: accepted 2/2 (K=3) + correction -> +3 tokens (111.1 ms) cpos=37
|
| 804 |
+
[margins] 11.66 6.73 1.60 2.63 0.60 K=5
|
| 805 |
+
verify 12: accepted 3/4 (K=5) + correction -> +4 tokens (133.3 ms) cpos=41
|
| 806 |
+
[margins] 9.43 7.72 10.88 7.63 6.46 K=6
|
| 807 |
+
verify 13: accepted 5/5 (K=6) + correction -> +6 tokens (150.3 ms) cpos=47
|
| 808 |
+
[margins] 10.49 10.00 10.50 9.28 7.40 K=6
|
| 809 |
+
verify 14: accepted 5/5 (K=6) + correction -> +6 tokens (157.0 ms) cpos=53
|
| 810 |
+
[margins] 10.71 10.69 8.15 10.36 7.29 K=6
|
| 811 |
+
verify 15: accepted 5/5 (K=6) + correction -> +6 tokens (149.5 ms) cpos=59
|
| 812 |
+
[margins] 11.46 10.64 11.12 8.21 6.39 K=6
|
| 813 |
+
verify 16: accepted 5/5 (K=6) + correction -> +6 tokens (157.4 ms) cpos=65
|
| 814 |
+
[margins] 9.71 10.86 9.03 7.93 6.90 K=6
|
| 815 |
+
verify 17: accepted 5/5 (K=6) + correction -> +6 tokens (155.1 ms) cpos=71
|
| 816 |
+
[margins] 11.26 12.10 13.05 8.57 5.44 K=6
|
| 817 |
+
verify 18: accepted 5/5 (K=6) + correction -> +6 tokens (160.9 ms) cpos=77
|
| 818 |
+
[margins] 10.01 10.91 11.18 9.21 5.11 K=6
|
| 819 |
+
verify 19: accepted 5/5 (K=6) + correction -> +6 tokens (152.6 ms) cpos=83
|
| 820 |
+
[margins] 10.46 12.82 9.93 9.53 3.89 K=6
|
| 821 |
+
verify 20: accepted 5/5 (K=6) + correction -> +6 tokens (163.1 ms) cpos=89
|
| 822 |
+
[margins] 11.69 12.76 13.76 9.67 7.11 K=6
|
| 823 |
+
verify 21: accepted 5/5 (K=6) + correction -> +6 tokens (155.1 ms) cpos=95
|
| 824 |
+
[margins] 11.60 11.46 13.53 10.75 8.18 K=6
|
| 825 |
+
verify 22: accepted 5/5 (K=6) + correction -> +6 tokens (162.3 ms) cpos=101
|
| 826 |
+
[margins] 9.47 11.90 10.98 8.23 4.96 K=6
|
| 827 |
+
verify 23: accepted 5/5 (K=6) + correction -> +6 tokens (155.4 ms) cpos=107
|
| 828 |
+
[margins] 11.48 12.65 12.07 10.30 6.88 K=6
|
| 829 |
+
verify 24: accepted 5/5 (K=6) + correction -> +6 tokens (163.2 ms) cpos=113
|
| 830 |
+
[margins] 10.59 9.97 14.86 9.32 7.23 K=6
|
| 831 |
+
verify 25: accepted 5/5 (K=6) + correction -> +6 tokens (154.5 ms) cpos=119
|
| 832 |
+
[margins] 10.54 11.38 9.45 9.76 6.88 K=6
|
| 833 |
+
verify 26: accepted 5/5 (K=6) + correction -> +6 tokens (163.3 ms) cpos=125
|
| 834 |
+
[margins] 11.80 11.53 12.53 9.30 8.42 K=6
|
| 835 |
+
verify 27: accepted 5/5 (K=6) + correction -> +6 tokens (170.1 ms) cpos=131
|
| 836 |
+
[margins] 11.39 11.84 11.89 9.26 5.51 K=6
|
| 837 |
+
verify 28: accepted 5/5 (K=6) + correction -> +6 tokens (162.0 ms) cpos=137
|
| 838 |
+
[margins] 11.72 13.61 12.48 9.89 8.95 K=6
|
| 839 |
+
verify 29: accepted 5/5 (K=6) + correction -> +6 tokens (154.6 ms) cpos=143
|
| 840 |
+
[margins] 11.95 12.37 13.28 10.28 8.48 K=6
|
| 841 |
+
verify 30: accepted 5/5 (K=6) + correction -> +6 tokens (161.9 ms) cpos=149
|
| 842 |
+
[margins] 10.92 12.46 12.51 9.57 6.06 K=6
|
| 843 |
+
verify 31: accepted 5/5 (K=6) + correction -> +6 tokens (154.8 ms) cpos=155
|
| 844 |
+
[margins] 11.85 11.98 13.41 8.58 7.51 K=6
|
| 845 |
+
verify 32: accepted 5/5 (K=6) + correction -> +6 tokens (164.7 ms) cpos=161
|
| 846 |
+
[margins] 10.80 12.44 12.97 10.15 8.00 K=6
|
| 847 |
+
verify 33: accepted 5/5 (K=6) + correction -> +6 tokens (157.2 ms) cpos=167
|
| 848 |
+
[margins] 11.51 12.97 10.32 9.25 8.34 K=6
|
| 849 |
+
verify 34: accepted 5/5 (K=6) + correction -> +6 tokens (163.6 ms) cpos=173
|
| 850 |
+
[margins] 11.13 13.54 12.46 8.45 3.95 K=6
|
| 851 |
+
verify 35: accepted 5/5 (K=6) + correction -> +6 tokens (157.3 ms) cpos=179
|
| 852 |
+
[margins] 11.88 12.29 12.80 10.32 4.99 K=6
|
| 853 |
+
verify 36: accepted 5/5 (K=6) + correction -> +6 tokens (164.4 ms) cpos=185
|
| 854 |
+
[margins] 12.29 12.14 13.36 9.73 7.75 K=6
|
| 855 |
+
verify 37: accepted 5/5 (K=6) + correction -> +6 tokens (160.0 ms) cpos=191
|
| 856 |
+
[margins] 10.79 12.82 11.86 8.57 5.53 K=6
|
| 857 |
+
verify 38: accepted 5/5 (K=6) + correction -> +6 tokens (164.5 ms) cpos=197
|
| 858 |
+
[margins] 10.38 11.56 11.37 9.49 6.13 K=6
|
| 859 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (158.3 ms) cpos=203
|
| 860 |
+
[margins] 11.67 12.52 10.93 8.83 5.50 K=6
|
| 861 |
+
verify 40: accepted 5/5 (K=6) + correction -> +6 tokens (164.3 ms) cpos=209
|
| 862 |
+
[margins] 10.85 12.81 13.39 8.69 3.37 K=6
|
| 863 |
+
verify 41: accepted 5/5 (K=6) + correction -> +6 tokens (158.9 ms) cpos=215
|
| 864 |
+
|
| 865 |
+
[spec] generated 201 tokens over 41 verifies: mean tokens/verify = 4.90 (block=5, max 6)
|
| 866 |
+
[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
|
| 867 |
+
[spec] SPEC-DECODE: 29.1 ms/tok = 34.33 tok/s (vs base M=1 68.6 ms/tok = 14.57 tok/s -> 2.36x)
|
| 868 |
+
[decode] PREFILL: 37 positions in 634.2 ms = 58.3 tok/s (17.140 ms/tok)
|
| 869 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=7 s=38)...
|
| 870 |
+
[margins] 0.14 0.24 0.43 0.01 0.45 K=2
|
| 871 |
+
verify 1: accepted 0/1 (K=2) + correction -> +1 tokens (100.4 ms) cpos=38
|
| 872 |
+
[margins] 0.77 6.09 0.34 1.09 0.34 K=3
|
| 873 |
+
verify 2: accepted 0/2 (K=3) + correction -> +1 tokens (111.4 ms) cpos=39
|
| 874 |
+
[margins] 1.40 0.28 5.25 0.37 0.62 K=2
|
| 875 |
+
verify 3: accepted 1/1 (K=2) + correction -> +2 tokens (99.8 ms) cpos=41
|
| 876 |
+
[margins] 3.42 0.18 0.21 6.65 0.01 K=2
|
| 877 |
+
verify 4: accepted 1/1 (K=2) + correction -> +2 tokens (96.1 ms) cpos=43
|
| 878 |
+
[margins] 1.07 1.59 0.53 0.24 0.19 K=3
|
| 879 |
+
verify 5: accepted 0/2 (K=3) + correction -> +1 tokens (111.4 ms) cpos=44
|
| 880 |
+
[margins] 0.36 0.01 0.82 0.15 0.24 K=2
|
| 881 |
+
verify 6: accepted 1/1 (K=2) + correction -> +2 tokens (95.6 ms) cpos=46
|
| 882 |
+
[margins] 1.11 1.39 1.56 0.27 0.66 K=2
|
| 883 |
+
verify 7: accepted 0/1 (K=2) + correction -> +1 tokens (101.9 ms) cpos=47
|
| 884 |
+
[margins] 3.40 2.61 0.25 0.45 1.72 K=3
|
| 885 |
+
verify 8: accepted 1/2 (K=3) + correction -> +2 tokens (113.9 ms) cpos=49
|
| 886 |
+
[margins] 8.08 7.02 4.41 2.04 0.87 K=5
|
| 887 |
+
verify 9: accepted 4/4 (K=5) + correction -> +5 tokens (138.3 ms) cpos=54
|
| 888 |
+
[margins] 0.76 0.29 1.30 2.37 0.79 K=2
|
| 889 |
+
verify 10: accepted 1/1 (K=2) + correction -> +2 tokens (102.4 ms) cpos=56
|
| 890 |
+
[margins] 5.39 2.63 1.15 0.38 0.52 K=3
|
| 891 |
+
verify 11: accepted 2/2 (K=3) + correction -> +3 tokens (107.8 ms) cpos=59
|
| 892 |
+
[margins] 3.99 2.31 0.09 0.21 0.06 K=3
|
| 893 |
+
verify 12: accepted 2/2 (K=3) + correction -> +3 tokens (113.6 ms) cpos=62
|
| 894 |
+
[margins] 2.27 2.17 4.15 0.97 2.55 K=4
|
| 895 |
+
verify 13: accepted 3/3 (K=4) + correction -> +4 tokens (126.6 ms) cpos=66
|
| 896 |
+
[margins] 13.86 3.56 5.65 0.54 0.70 K=4
|
| 897 |
+
verify 14: accepted 3/3 (K=4) + correction -> +4 tokens (129.1 ms) cpos=70
|
| 898 |
+
[margins] 0.82 0.82 0.12 1.56 0.44 K=2
|
| 899 |
+
verify 15: accepted 1/1 (K=2) + correction -> +2 tokens (101.9 ms) cpos=72
|
| 900 |
+
[margins] 2.44 6.11 0.22 0.23 0.15 K=3
|
| 901 |
+
verify 16: accepted 2/2 (K=3) + correction -> +3 tokens (109.0 ms) cpos=75
|
| 902 |
+
[margins] 1.86 8.25 0.09 1.18 1.64 K=3
|
| 903 |
+
verify 17: accepted 2/2 (K=3) + correction -> +3 tokens (112.1 ms) cpos=78
|
| 904 |
+
[margins] 7.75 7.75 5.59 8.01 8.69 K=6
|
| 905 |
+
verify 18: accepted 5/5 (K=6) + correction -> +6 tokens (160.8 ms) cpos=84
|
| 906 |
+
[margins] 9.07 8.06 6.36 5.57 0.09 K=5
|
| 907 |
+
verify 19: accepted 4/4 (K=5) + correction -> +5 tokens (142.3 ms) cpos=89
|
| 908 |
+
[margins] 8.42 5.82 4.97 0.82 0.80 K=4
|
| 909 |
+
verify 20: accepted 3/3 (K=4) + correction -> +4 tokens (128.6 ms) cpos=93
|
| 910 |
+
[margins] 4.49 3.09 0.94 0.41 0.79 K=3
|
| 911 |
+
verify 21: accepted 2/2 (K=3) + correction -> +3 tokens (115.2 ms) cpos=96
|
| 912 |
+
[margins] 10.55 8.36 5.92 7.71 10.32 K=6
|
| 913 |
+
verify 22: accepted 5/5 (K=6) + correction -> +6 tokens (160.2 ms) cpos=102
|
| 914 |
+
[margins] 16.78 9.32 4.05 2.78 2.30 K=6
|
| 915 |
+
verify 23: accepted 5/5 (K=6) + correction -> +6 tokens (165.8 ms) cpos=108
|
| 916 |
+
[margins] 9.52 10.75 3.40 2.44 3.91 K=6
|
| 917 |
+
verify 24: accepted 5/5 (K=6) + correction -> +6 tokens (161.9 ms) cpos=114
|
| 918 |
+
[margins] 12.05 4.17 5.41 6.23 9.15 K=6
|
| 919 |
+
verify 25: accepted 5/5 (K=6) + correction -> +6 tokens (165.5 ms) cpos=120
|
| 920 |
+
[margins] 14.58 9.44 6.89 9.43 0.29 K=5
|
| 921 |
+
verify 26: accepted 4/4 (K=5) + correction -> +5 tokens (144.1 ms) cpos=125
|
| 922 |
+
[margins] 6.91 7.95 2.31 6.31 3.64 K=6
|
| 923 |
+
verify 27: accepted 5/5 (K=6) + correction -> +6 tokens (175.0 ms) cpos=131
|
| 924 |
+
[margins] 0.35 6.30 0.62 3.08 1.19 K=3
|
| 925 |
+
verify 28: accepted 2/2 (K=3) + correction -> +3 tokens (116.3 ms) cpos=134
|
| 926 |
+
[margins] 13.18 5.27 0.58 0.64 1.17 K=3
|
| 927 |
+
verify 29: accepted 2/2 (K=3) + correction -> +3 tokens (119.0 ms) cpos=137
|
| 928 |
+
[margins] 2.56 0.15 1.01 0.21 0.64 K=2
|
| 929 |
+
verify 30: accepted 1/1 (K=2) + correction -> +2 tokens (103.0 ms) cpos=139
|
| 930 |
+
[margins] 7.66 0.50 6.12 7.11 4.79 K=2
|
| 931 |
+
verify 31: accepted 1/1 (K=2) + correction -> +2 tokens (104.3 ms) cpos=141
|
| 932 |
+
[margins] 10.01 8.87 5.03 2.06 0.80 K=5
|
| 933 |
+
verify 32: accepted 4/4 (K=5) + correction -> +5 tokens (146.0 ms) cpos=146
|
| 934 |
+
[margins] 5.98 10.82 10.20 11.03 2.76 K=6
|
| 935 |
+
verify 33: accepted 4/5 (K=6) + correction -> +5 tokens (169.2 ms) cpos=151
|
| 936 |
+
[margins] 2.40 0.03 0.06 0.41 1.88 K=2
|
| 937 |
+
verify 34: accepted 1/1 (K=2) + correction -> +2 tokens (110.0 ms) cpos=153
|
| 938 |
+
[margins] 2.50 4.99 2.40 0.05 1.07 K=4
|
| 939 |
+
verify 35: accepted 0/3 (K=4) + correction -> +1 tokens (120.6 ms) cpos=154
|
| 940 |
+
[margins] 7.38 2.46 0.28 1.52 2.06 K=3
|
| 941 |
+
verify 36: accepted 1/2 (K=3) + correction -> +2 tokens (115.6 ms) cpos=156
|
| 942 |
+
[margins] 6.30 4.43 0.57 0.07 3.04 K=3
|
| 943 |
+
verify 37: accepted 1/2 (K=3) + correction -> +2 tokens (109.9 ms) cpos=158
|
| 944 |
+
[margins] 4.39 0.32 3.44 0.28 1.69 K=2
|
| 945 |
+
verify 38: accepted 1/1 (K=2) + correction -> +2 tokens (108.2 ms) cpos=160
|
| 946 |
+
[margins] 5.00 4.43 3.60 1.31 2.83 K=4
|
| 947 |
+
verify 39: accepted 3/3 (K=4) + correction -> +4 tokens (124.7 ms) cpos=164
|
| 948 |
+
[margins] 3.48 7.07 4.15 4.40 3.93 K=6
|
| 949 |
+
verify 40: accepted 5/5 (K=6) + correction -> +6 tokens (149.4 ms) cpos=170
|
| 950 |
+
[margins] 2.28 8.11 1.80 6.74 4.28 K=6
|
| 951 |
+
verify 41: accepted 5/5 (K=6) + correction -> +6 tokens (155.7 ms) cpos=176
|
| 952 |
+
[margins] 2.12 9.33 2.62 6.35 3.90 K=6
|
| 953 |
+
verify 42: accepted 5/5 (K=6) + correction -> +6 tokens (150.2 ms) cpos=182
|
| 954 |
+
[margins] 3.16 9.65 3.45 6.38 4.73 K=6
|
| 955 |
+
verify 43: accepted 5/5 (K=6) + correction -> +6 tokens (156.5 ms) cpos=188
|
| 956 |
+
[margins] 3.12 8.81 3.30 5.90 5.11 K=6
|
| 957 |
+
verify 44: accepted 5/5 (K=6) + correction -> +6 tokens (150.1 ms) cpos=194
|
| 958 |
+
[margins] 2.99 9.57 2.92 6.75 4.69 K=6
|
| 959 |
+
verify 45: accepted 5/5 (K=6) + correction -> +6 tokens (156.2 ms) cpos=200
|
| 960 |
+
[margins] 2.48 9.20 3.18 6.80 4.17 K=6
|
| 961 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (150.5 ms) cpos=206
|
| 962 |
+
[margins] 2.40 9.47 2.82 7.30 4.35 K=6
|
| 963 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (157.1 ms) cpos=212
|
| 964 |
+
[margins] 2.79 9.74 2.77 7.22 4.29 K=6
|
| 965 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (149.4 ms) cpos=218
|
| 966 |
+
[margins] 2.78 9.73 4.21 6.44 3.98 K=6
|
| 967 |
+
verify 49: accepted 5/5 (K=6) + correction -> +6 tokens (156.4 ms) cpos=224
|
| 968 |
+
[margins] 2.58 10.59 2.85 6.99 3.44 K=6
|
| 969 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (150.1 ms) cpos=230
|
| 970 |
+
[margins] 3.13 9.87 3.44 6.19 3.83 K=6
|
| 971 |
+
verify 51: accepted 0/5 (K=6) + correction -> +1 tokens (156.7 ms) cpos=231
|
| 972 |
+
[margins] 8.66 1.83 3.78 4.26 4.17 K=6
|
| 973 |
+
verify 52: accepted 0/5 (K=6) + correction -> +1 tokens (161.9 ms) cpos=232
|
| 974 |
+
[margins] 6.69 0.60 8.18 1.47 1.34 K=2
|
| 975 |
+
verify 53: accepted 1/1 (K=2) + correction -> +2 tokens (101.2 ms) cpos=234
|
| 976 |
+
[margins] 5.78 0.99 3.39 0.80 1.14 K=2
|
| 977 |
+
verify 54: accepted 1/1 (K=2) + correction -> +2 tokens (105.6 ms) cpos=236
|
| 978 |
+
[margins] 4.58 0.19 8.22 0.30 0.87 K=2
|
| 979 |
+
verify 55: accepted 0/1 (K=2) + correction -> +1 tokens (101.4 ms) cpos=237
|
| 980 |
+
|
| 981 |
+
[spec] generated 200 tokens over 55 verifies: mean tokens/verify = 3.64 (block=5, max 6)
|
| 982 |
+
[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
|
| 983 |
+
[spec] SPEC-DECODE: 35.4 ms/tok = 28.24 tok/s (vs base M=1 68.6 ms/tok = 14.57 tok/s -> 1.94x)
|
| 984 |
+
[decode] PREFILL: 12 positions in 252.5 ms = 47.5 tok/s (21.044 ms/tok)
|
| 985 |
+
[spec] decoding 200 tokens (block=5, draft passes=1, adaptK=1.50, prompt=8 s=13)...
|
| 986 |
+
[margins] 2.65 0.36 0.13 0.93 1.09 K=2
|
| 987 |
+
verify 1: accepted 1/1 (K=2) + correction -> +2 tokens (99.0 ms) cpos=14
|
| 988 |
+
[margins] 0.65 6.84 3.26 0.54 5.69 K=4
|
| 989 |
+
verify 2: accepted 0/3 (K=4) + correction -> +1 tokens (127.8 ms) cpos=15
|
| 990 |
+
[margins] 2.65 2.80 0.02 2.28 1.27 K=3
|
| 991 |
+
verify 3: accepted 0/2 (K=3) + correction -> +1 tokens (103.4 ms) cpos=16
|
| 992 |
+
[margins] 3.81 1.15 0.56 0.50 0.89 K=2
|
| 993 |
+
verify 4: accepted 0/1 (K=2) + correction -> +1 tokens (95.2 ms) cpos=17
|
| 994 |
+
[margins] 4.04 4.39 0.17 3.01 0.47 K=3
|
| 995 |
+
verify 5: accepted 0/2 (K=3) + correction -> +1 tokens (102.7 ms) cpos=18
|
| 996 |
+
[margins] 0.14 0.04 0.17 0.07 0.99 K=2
|
| 997 |
+
verify 6: accepted 0/1 (K=2) + correction -> +1 tokens (99.6 ms) cpos=19
|
| 998 |
+
[margins] 0.01 3.21 0.61 0.09 0.47 K=3
|
| 999 |
+
verify 7: accepted 2/2 (K=3) + correction -> +3 tokens (108.7 ms) cpos=22
|
| 1000 |
+
[margins] 1.35 5.34 0.78 4.09 0.76 K=3
|
| 1001 |
+
verify 8: accepted 0/2 (K=3) + correction -> +1 tokens (108.9 ms) cpos=23
|
| 1002 |
+
[margins] 0.49 1.37 0.68 0.64 0.65 K=2
|
| 1003 |
+
verify 9: accepted 1/1 (K=2) + correction -> +2 tokens (103.0 ms) cpos=25
|
| 1004 |
+
[margins] 1.98 1.62 1.78 0.48 0.80 K=4
|
| 1005 |
+
verify 10: accepted 3/3 (K=4) + correction -> +4 tokens (118.1 ms) cpos=29
|
| 1006 |
+
[margins] 4.31 1.27 3.87 0.63 4.62 K=2
|
| 1007 |
+
verify 11: accepted 1/1 (K=2) + correction -> +2 tokens (98.9 ms) cpos=31
|
| 1008 |
+
[margins] 4.89 1.51 4.58 0.34 4.66 K=4
|
| 1009 |
+
verify 12: accepted 3/3 (K=4) + correction -> +4 tokens (118.8 ms) cpos=35
|
| 1010 |
+
[margins] 6.25 1.08 5.86 0.42 5.35 K=2
|
| 1011 |
+
verify 13: accepted 1/1 (K=2) + correction -> +2 tokens (102.9 ms) cpos=37
|
| 1012 |
+
[margins] 5.69 1.95 5.05 0.58 4.52 K=4
|
| 1013 |
+
verify 14: accepted 3/3 (K=4) + correction -> +4 tokens (118.8 ms) cpos=41
|
| 1014 |
+
[margins] 5.79 1.54 5.18 0.83 4.48 K=4
|
| 1015 |
+
verify 15: accepted 3/3 (K=4) + correction -> +4 tokens (121.9 ms) cpos=45
|
| 1016 |
+
[margins] 6.84 0.72 4.98 1.62 3.96 K=2
|
| 1017 |
+
verify 16: accepted 0/1 (K=2) + correction -> +1 tokens (100.3 ms) cpos=46
|
| 1018 |
+
[margins] 5.25 3.76 6.07 1.10 1.25 K=4
|
| 1019 |
+
verify 17: accepted 3/3 (K=4) + correction -> +4 tokens (128.8 ms) cpos=50
|
| 1020 |
+
[margins] 2.95 1.73 0.69 0.65 1.73 K=3
|
| 1021 |
+
verify 18: accepted 2/2 (K=3) + correction -> +3 tokens (113.6 ms) cpos=53
|
| 1022 |
+
[margins] 8.07 9.22 0.06 3.51 0.49 K=3
|
| 1023 |
+
verify 19: accepted 2/2 (K=3) + correction -> +3 tokens (111.8 ms) cpos=56
|
| 1024 |
+
[margins] 3.30 1.47 2.98 0.50 1.76 K=2
|
| 1025 |
+
verify 20: accepted 1/1 (K=2) + correction -> +2 tokens (100.5 ms) cpos=58
|
| 1026 |
+
[margins] 0.19 7.64 0.11 0.43 1.07 K=3
|
| 1027 |
+
verify 21: accepted 0/2 (K=3) + correction -> +1 tokens (111.0 ms) cpos=59
|
| 1028 |
+
[margins] 1.69 1.49 0.93 1.39 0.38 K=2
|
| 1029 |
+
verify 22: accepted 0/1 (K=2) + correction -> +1 tokens (102.1 ms) cpos=60
|
| 1030 |
+
[margins] 4.86 1.59 6.61 7.44 3.82 K=6
|
| 1031 |
+
verify 23: accepted 5/5 (K=6) + correction -> +6 tokens (154.6 ms) cpos=66
|
| 1032 |
+
[margins] 8.24 9.58 9.47 1.67 0.06 K=5
|
| 1033 |
+
verify 24: accepted 3/4 (K=5) + correction -> +4 tokens (141.3 ms) cpos=70
|
| 1034 |
+
[margins] 0.65 5.63 0.42 3.44 0.34 K=3
|
| 1035 |
+
verify 25: accepted 0/2 (K=3) + correction -> +1 tokens (115.3 ms) cpos=71
|
| 1036 |
+
[margins] 1.52 4.28 4.21 2.24 2.26 K=6
|
| 1037 |
+
verify 26: accepted 0/5 (K=6) + correction -> +1 tokens (161.8 ms) cpos=72
|
| 1038 |
+
[margins] 3.36 1.66 5.24 7.42 3.05 K=6
|
| 1039 |
+
verify 27: accepted 5/5 (K=6) + correction -> +6 tokens (156.5 ms) cpos=78
|
| 1040 |
+
[margins] 7.11 9.29 7.41 0.96 0.01 K=4
|
| 1041 |
+
verify 28: accepted 3/3 (K=4) + correction -> +4 tokens (129.2 ms) cpos=82
|
| 1042 |
+
[margins] 3.31 5.41 1.43 3.42 3.61 K=3
|
| 1043 |
+
verify 29: accepted 2/2 (K=3) + correction -> +3 tokens (115.5 ms) cpos=85
|
| 1044 |
+
[margins] 4.40 8.18 1.86 2.50 6.74 K=6
|
| 1045 |
+
verify 30: accepted 5/5 (K=6) + correction -> +6 tokens (157.1 ms) cpos=91
|
| 1046 |
+
[margins] 4.32 12.56 0.85 2.80 4.24 K=3
|
| 1047 |
+
verify 31: accepted 2/2 (K=3) + correction -> +3 tokens (116.5 ms) cpos=94
|
| 1048 |
+
[margins] 4.75 6.79 7.00 4.04 3.57 K=6
|
| 1049 |
+
verify 32: accepted 5/5 (K=6) + correction -> +6 tokens (165.2 ms) cpos=100
|
| 1050 |
+
[margins] 4.95 5.95 3.53 5.86 0.98 K=5
|
| 1051 |
+
verify 33: accepted 4/4 (K=5) + correction -> +5 tokens (143.8 ms) cpos=105
|
| 1052 |
+
[margins] 3.32 4.96 3.67 4.19 6.55 K=6
|
| 1053 |
+
verify 34: accepted 5/5 (K=6) + correction -> +6 tokens (159.4 ms) cpos=111
|
| 1054 |
+
[margins] 8.04 2.58 3.61 0.31 4.82 K=4
|
| 1055 |
+
verify 35: accepted 3/3 (K=4) + correction -> +4 tokens (131.7 ms) cpos=115
|
| 1056 |
+
[margins] 5.58 15.40 2.18 5.38 8.24 K=6
|
| 1057 |
+
verify 36: accepted 5/5 (K=6) + correction -> +6 tokens (166.4 ms) cpos=121
|
| 1058 |
+
[margins] 5.38 9.72 5.78 5.80 6.19 K=6
|
| 1059 |
+
verify 37: accepted 5/5 (K=6) + correction -> +6 tokens (158.8 ms) cpos=127
|
| 1060 |
+
[margins] 5.38 14.53 2.83 6.26 9.39 K=6
|
| 1061 |
+
verify 38: accepted 5/5 (K=6) + correction -> +6 tokens (182.9 ms) cpos=133
|
| 1062 |
+
[margins] 5.56 11.98 7.60 4.13 7.13 K=6
|
| 1063 |
+
verify 39: accepted 5/5 (K=6) + correction -> +6 tokens (160.9 ms) cpos=139
|
| 1064 |
+
[margins] 5.51 9.71 2.57 5.85 7.31 K=6
|
| 1065 |
+
verify 40: accepted 5/5 (K=6) + correction -> +6 tokens (167.6 ms) cpos=145
|
| 1066 |
+
[margins] 7.35 10.60 7.46 3.50 8.42 K=6
|
| 1067 |
+
verify 41: accepted 5/5 (K=6) + correction -> +6 tokens (160.5 ms) cpos=151
|
| 1068 |
+
[margins] 5.69 13.35 2.07 7.00 6.68 K=6
|
| 1069 |
+
verify 42: accepted 5/5 (K=6) + correction -> +6 tokens (167.1 ms) cpos=157
|
| 1070 |
+
[margins] 8.78 10.47 6.80 4.53 7.31 K=6
|
| 1071 |
+
verify 43: accepted 5/5 (K=6) + correction -> +6 tokens (162.5 ms) cpos=163
|
| 1072 |
+
[margins] 5.80 12.78 2.58 7.14 6.30 K=6
|
| 1073 |
+
verify 44: accepted 5/5 (K=6) + correction -> +6 tokens (167.6 ms) cpos=169
|
| 1074 |
+
[margins] 8.93 8.05 8.46 4.72 1.24 K=5
|
| 1075 |
+
verify 45: accepted 4/4 (K=5) + correction -> +5 tokens (144.0 ms) cpos=174
|
| 1076 |
+
[margins] 13.94 12.08 9.86 1.62 5.07 K=6
|
| 1077 |
+
verify 46: accepted 5/5 (K=6) + correction -> +6 tokens (166.9 ms) cpos=180
|
| 1078 |
+
[margins] 5.89 8.82 10.16 8.93 5.65 K=6
|
| 1079 |
+
verify 47: accepted 5/5 (K=6) + correction -> +6 tokens (161.6 ms) cpos=186
|
| 1080 |
+
[margins] 12.86 9.29 9.80 1.98 5.70 K=6
|
| 1081 |
+
verify 48: accepted 5/5 (K=6) + correction -> +6 tokens (167.1 ms) cpos=192
|
| 1082 |
+
[margins] 4.69 7.94 9.50 8.28 6.24 K=6
|
| 1083 |
+
verify 49: accepted 5/5 (K=6) + correction -> +6 tokens (162.2 ms) cpos=198
|
| 1084 |
+
[margins] 15.25 10.40 8.74 2.02 5.14 K=6
|
| 1085 |
+
verify 50: accepted 5/5 (K=6) + correction -> +6 tokens (166.8 ms) cpos=204
|
| 1086 |
+
[margins] 4.29 8.18 9.53 8.22 6.69 K=6
|
| 1087 |
+
verify 51: accepted 5/5 (K=6) + correction -> +6 tokens (163.3 ms) cpos=210
|
| 1088 |
+
[margins] 13.47 11.18 8.65 2.02 4.80 K=6
|
| 1089 |
+
verify 52: accepted 5/5 (K=6) + correction -> +6 tokens (167.7 ms) cpos=216
|
| 1090 |
+
|
| 1091 |
+
[spec] generated 204 tokens over 52 verifies: mean tokens/verify = 3.92 (block=5, max 6)
|
| 1092 |
+
[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
|
| 1093 |
+
[spec] SPEC-DECODE: 34.3 ms/tok = 29.11 tok/s (vs base M=1 68.6 ms/tok = 14.57 tok/s -> 2.00x)
|
| 1094 |
+
|
| 1095 |
+
[blksweep] BLK passes adaptK->eff prompt | mean tok/verify | ms/tok | tok/s | vs base 14.57 tok/s
|
| 1096 |
+
[blksweep] 5 1 1.50 1.50 0 | 3.26 | 39.5 | 25.35 | 1.74x
|
| 1097 |
+
[blksweep] 5 1 1.50 1.50 1 | 4.00 | 34.8 | 28.72 | 1.97x
|
| 1098 |
+
[blksweep] 5 1 1.50 1.50 2 | 4.04 | 35.1 | 28.45 | 1.95x
|
| 1099 |
+
[blksweep] 5 1 1.50 1.50 3 | 2.52 | 47.4 | 21.08 | 1.45x
|
| 1100 |
+
[blksweep] 5 1 1.50 1.50 4 | 3.06 | 39.9 | 25.04 | 1.72x
|
| 1101 |
+
[blksweep] 5 1 1.50 1.50 5 | 4.34 | 34.3 | 29.18 | 2.00x
|
| 1102 |
+
[blksweep] 5 1 1.50 1.50 6 | 4.90 | 29.1 | 34.33 | 2.36x
|
| 1103 |
+
[blksweep] 5 1 1.50 1.50 7 | 3.64 | 35.4 | 28.24 | 1.94x
|
| 1104 |
+
[blksweep] 5 1 1.50 1.50 8 | 3.92 | 34.3 | 29.11 | 2.00x
|
| 1105 |
+
[decode] mem 106.6/122.8 GiB
|