Table 8 reports per-method batch size, tokens committed per verification, acceptance rate, average generated length, and homogeneous draft/verify step timings for LB[16k-18k] on all three models.

Table 8 reports per-method batch size, tokens committed per verification, acceptance rate, average generated length, and homogeneous draft/verify step timings for LB[16k-18k] on all three models. · CiteArk

测量结果

已评估 0/81 项

获得支持 0有争议或冲突 0尚未评估 81

保留同一结论下的完整结果组。已有评估排在前面；单项判断不替代整组结论。展开行查看条件、来源与历次证据。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
指标与条件	论文报告	最近可用实测	证据判断
model: Qwen3-1.7B · method: ASPIRE · dataset: LB[16k-18k]	35 requests	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE · dataset: LB[16k-18k]	14.78 tokens/verification	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE · dataset: LB[16k-18k]	97.2%	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE · dataset: LB[16k-18k]	202 tokens/request	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE · dataset: LB[16k-18k]	5.93 ms/forward step	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE-Fixed · dataset: LB[16k-18k]	35 requests	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE-Fixed · dataset: LB[16k-18k]	5.78 tokens/verification	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE-Fixed · dataset: LB[16k-18k]	93.4%	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE-Fixed · dataset: LB[16k-18k]	71 tokens/request	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE-Fixed · dataset: LB[16k-18k]	6.16 ms/forward step	—	尚未评估
model: Qwen3-1.7B · method: ASPIRE-Fixed · dataset: LB[16k-18k]	29.21 ms/forward step	—	尚未评估
model: Qwen3-1.7B · method: Vegas · dataset: LB[16k-18k]	35 requests	—	尚未评估

Table 8 reports per-method batch size, tokens committed per verification, acceptance rate, average generated length, and homogeneous draft/verify step timings for LB[16k-18k] on all three models.

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果