A DFlash2 draft for greedy speculative decoding with Qwen3-ASR-1.7B (Qwen/Qwen3-ASR-1.7B and Qwen/Qwen3-ASR-1.7B-hf), in the speculators dflash2 format.
wilsonzheng0327/Qwen3-ASR-1.7B-dflash at d62bd4051e and trained further on the same sources.This is a pilot.
| setting | value |
|---|---|
| backbone | the DFlash draft's: fc, hidden_norm, 5 Qwen3 layers (hidden 2048, intermediate 6144, 16 heads / 8 KV heads, head_dim 128), norm |
| DFlash2 additions | grouped dynamic causal convolutions (kernel 2, group 16, identity-initialized) and a candidate selector (rank 256) that reranks the target head's top 16 per position |
| vocabulary | the full 151,936-token vocabulary; the draft has no lm_head of its own and uses the target's |
| target aux layers | 2, 14, 25 (hidden states entering those layers) |
| block size | 8 (7 proposals per round, anchor = last committed token), causal within the block |
| mask token | 151705 |
| sliding window | 32,768 |
| parameters | 353.2M (backbone 264.3M, selector 78.3M, convolutions 10.6M) |
| precision | bf16 (cast from the float32 training checkpoint) |
7ed657f, 30,500 steps planned (5.58 epochs). The shipped checkpoint is step 16,181, which had the best short + long accept on the 360-clip check subset; accept was flat after it.These numbers come from simulated greedy speculative decoding on CUDA with a bf16 target. The sets and labels are the published draft's held-out sets and the same target labels. The published draft's own row reproduces its card (5.43 short).
| draft | Libri clean | Libri other | FLEURS en | Emilia en | FLEURS zh | Emilia zh | CV ja | FLEURS ja | Emilia ja | en | zh | ja | all | 60 s en | 60 s zh | 60 s ja | 180 s en | 180 s zh | 180 s ja | long all |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| published DFlash draft | 6.43 | 5.88 | 5.79 | 6.12 | 5.62 | 5.59 | 4.51 | 4.99 | 4.32 | 6.09 | 5.60 | 4.61 | 5.43 | 6.24 | 5.74 | 4.74 | 6.15 | 5.64 | 4.69 | 5.57 |
| DFlash control | 6.43 | 6.04 | 5.87 | 6.08 | 5.64 | 5.57 | 4.52 | 5.00 | 4.28 | 6.13 | 5.60 | 4.60 | 5.44 | 6.23 | 5.86 | 4.73 | 6.21 | 5.77 | 4.65 | 5.60 |
| this draft, with the selector | 6.56 | 6.13 | 6.07 | 6.37 | 5.96 | 5.76 | 4.86 | 5.34 | 4.59 | 6.32 | 5.84 | 4.93 | 5.70 | 6.53 | 6.14 | 5.09 | 6.47 | 6.01 | 5.00 | 5.91 |
| this draft, without the selector | 6.46 | 6.05 | 5.98 | 6.26 | 5.89 | 5.62 | 4.56 | 5.04 | 4.30 | 6.22 | 5.73 | 4.63 | 5.51 | 6.31 | 5.86 | 4.75 | 6.35 | 5.76 | 4.63 | 5.64 |
eval/.Setup:
| draft | served accept en | served accept zh | en c1 | en c4 | en c16 | zh c1 | zh c4 | zh c16 |
|---|---|---|---|---|---|---|---|---|
| published DFlash draft | 4.57 | 3.97 | 1.74x | 1.56x | 1.28x | 1.53x | 1.36x | 1.13x |
| this draft | 4.70 | 4.25 | 1.70x | 1.52x | 1.26x | 1.55x | 1.39x | 1.17x |
Apache-2.0, as the target model and the published DFlash draft.
Qwen/Qwen3-ASR-1.7B