Views
No views yet
Qwen/Qwen3-8Bexisting bf16 file backend)inference-optimization/Dataset-Qwen3-235B-Instruct...-fp8ablation-bf16 / ...-fp8ablation-fp8) trained
identically except for the hidden-states transfer precision, to isolate the effect of
FP8 quantization on speculator quality. See the sibling repo for the other precision.loss_epoch: 0.670712full_acc_epoch: 0.190457position_1_acc_epoch: 0.671505position_2_acc_epoch: 0.470419position_3_acc_epoch: 0.345403position_4_acc_epoch: 0.259921position_5_acc_epoch: 0.199261position_6_acc_epoch: 0.156393position_7_acc_epoch: 0.125580position_8_acc_epoch: 0.105085position_9_acc_epoch: 0.090258position_10_acc_epoch: 0.081353position_11_acc_epoch: 0.075329position_12_acc_epoch: 0.070879position_13_acc_epoch: 0.068388position_14_acc_epoch: 0.065941position_15_acc_epoch: 0.063810eal_epoch: 1.165076acceptance.csv in this repo for the full per-subset guidellm breakdown (9 subset rows).