File size: 4,033 Bytes
b5bff9c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 | nohup: ignoring input
Loading model...
[Auto-detect] Qwen3-Omni MoE thinker (30.5B total, ~3.3B active)
[FireEcho] Loading /run/media/echo/Echo/ECHO/training/Prototype Fireecho/model/Qwen3-Omni-30B-A3B-Instruct...
[FireEcho] AutoConfig failed ('Qwen3OmniMoeTalkerCodePredictorConfig' object has no attribute 'use_sliding_window'), loading config.json directly
Qwen3-Omni: will stream-load from 15 shards
[Qwen3 Streaming] Loaded shard index: 28010 keys across 15 shards
[Qwen3 Streaming] Building engine skeleton...
[Qwen3 Streaming] Global params on GPU: 1.2 GB
Layer 4/48: 393 weights, VRAM 2.8 GB, CPU 1.4 GB
Layer 8/48: 393 weights, VRAM 4.3 GB, CPU 1.6 GB
Layer 12/48: 393 weights, VRAM 5.8 GB, CPU 1.7 GB
Layer 16/48: 393 weights, VRAM 7.4 GB, CPU 1.9 GB
Layer 20/48: 393 weights, VRAM 8.9 GB, CPU 2.0 GB
Layer 24/48: 393 weights, VRAM 10.4 GB, CPU 2.2 GB
Layer 28/48: 393 weights, VRAM 11.9 GB, CPU 2.3 GB
Layer 32/48: 393 weights, VRAM 13.5 GB, CPU 2.5 GB
Layer 36/48: 393 weights, VRAM 15.0 GB, CPU 2.6 GB
Layer 40/48: 393 weights, VRAM 16.5 GB, CPU 2.8 GB
Layer 44/48: 393 weights, VRAM 18.0 GB, CPU 2.9 GB
Layer 48/48: 393 weights, VRAM 19.6 GB, CPU 3.1 GB
[Qwen3 Streaming] Final VRAM: 19.6 GB (FP4 quantized)
[Qwen3 Streaming] Done: 1571.8M params, 18867 weights loaded
Total params: 1.57B
Frozen params: 1.54B (base model, FP4)
Trainable params: 30.2M (Hebbian only)
[Packed MoE] 48 layers packed (6144 experts → contiguous)
[Flat KV] Enabled: 4096 tokens, 403 MB
Warmup...
============================================================
Testing D=2 (D=2 baseline)
============================================================
[EAGLE] Loaded legacy D=2 checkpoint. 0 new layer params initialized randomly.
[EAGLE-3] Draft head: D=2, 104.9M params, 210 MB, capture layers [8, 24, 47] + Hebbian memory
Target prefill logits: has_nan=True, min=nan, max=nan
First decoded token: 0 = '!'
Target predicts next: 0 = '!'
Feature layer 8: has_nan=True, min=nan, max=nan
Feature layer 24: has_nan=True, min=nan, max=nan
Feature layer 47: has_nan=True, min=nan, max=nan
Draft tokens:
[0] 0 = '!'
[1] 0 = '!'
[2] 0 = '!'
[3] 0 = '!'
[4] 0 = '!'
Draft logits[0]: has_nan=True, min=nan, max=nan
Target verify predictions:
[1] target=0 ('!'), draft=0 ('!') → MATCH
[2] target=0 ('!'), draft=0 ('!') → MATCH
[3] target=0 ('!'), draft=0 ('!') → MATCH
[4] target=0 ('!'), draft=0 ('!') → MATCH
Accepted: 5/5
--- Full speculative_generate (max_new=30) ---
[EAGLE-3] 5 rounds, 21 drafted, 21 accepted (100%), avg 4.2/round
Output: !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
============================================================
Testing D=8 (D=8 with random layers 2-7)
============================================================
[EAGLE] Loaded legacy D=2 checkpoint. 54 new layer params initialized randomly.
[FE-XT] Draft head: D=8, 356.5M params, 713 MB, capture layers [8, 24, 47] + Hebbian memory
Target prefill logits: has_nan=True, min=nan, max=nan
First decoded token: 0 = '!'
Target predicts next: 0 = '!'
Feature layer 8: has_nan=True, min=nan, max=nan
Feature layer 24: has_nan=True, min=nan, max=nan
Feature layer 47: has_nan=True, min=nan, max=nan
Draft tokens:
[0] 0 = '!'
[1] 0 = '!'
[2] 0 = '!'
[3] 0 = '!'
[4] 0 = '!'
Draft logits[0]: has_nan=True, min=nan, max=nan
Target verify predictions:
[1] target=0 ('!'), draft=0 ('!') → MATCH
[2] target=0 ('!'), draft=0 ('!') → MATCH
[3] target=0 ('!'), draft=0 ('!') → MATCH
[4] target=0 ('!'), draft=0 ('!') → MATCH
Accepted: 5/5
--- Full speculative_generate (max_new=30) ---
[EAGLE-3] 5 rounds, 21 drafted, 21 accepted (100%), avg 4.2/round
Output: !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
============================================================
D=2 accepted: 5/5
D=8 accepted: 5/5
============================================================
|