Downloads · 30 days
50
68% of all-time downloads
ctest-Qwen3-8B-speculator.dflash-fp8ablation-bf16
inference-optimization/ctest-Qwen3-8B-speculator.dflash-fp8ablation-bf16
ctest-Qwen3-8B-speculator.dflash-fp8ablation-bf16 is a machine learning model from inference-optimization. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Test checkpoint — not a production release. Trained to validate the FP8-quantized hidden-states transfer backend added in vllm-project/speculators1028 (draft, reviving 491).
All-time downloads
73
Public
Parameters
1.8B
3.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.5 GB · 100%
Parameter types
How the weights are stored.
BF161.8B · 100%
Model card
From the Hugging Face model README
ctest: Qwen3-8B DFlash speculator — FP8 hidden-states ablation (bf16)
Test checkpoint — not a production release. Trained to validate the FP8-quantized hidden-states transfer backend added in vllm-project/speculators#1028 (draft, reviving #491).
- Verifier:
Qwen/Qwen3-8B - Algorithm: dflash
- Hidden-states precision during training: bf16 (
existing bf16 file backend) - Training data: 5K magpie + 5K ultrachat samples from
inference-optimization/Dataset-Qwen3-235B-Instruct
This is one of a matched pair (...-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.
Validation metrics (final epoch)
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: 1.165076
guidellm serving eval
See acceptance.csv in this repo for the full per-subset guidellm breakdown (9 subset rows).
Full ablation writeup, all 6 checkpoints' results, exact commands, and code: see the results package referenced from PR #1028.
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026