Qwen3.8-27B-DSpark-FP8-DYNAMIC

An FP8 dynamic, data-free DSpark drafter derived from RedHatAI/Qwen3.8-27B-speculator.dspark at revision 7f33c272e5da240978e0d55767abab8193d74b95. Pair it with Qwen/Qwen3.8-27B at revision 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0. This repository contains a drafter component, not a standalone chat model.

Quantization

Data-free FP8_DYNAMIC export; no calibration data was used.

No calibration data was used for this data-free export. Quantization commands, manifests, source files, patches, and the exported checkpoint checksum are in provenance/quantization/.

Example serving command

vllm serve Qwen/Qwen3.8-27B \
  --spec-model inference-optimization/Qwen3.8-27B-DSpark-FP8-DYNAMIC \
  --spec-method dspark \
  --spec-tokens 8

This command is an example; this checkpoint has not completed serving validation.

Evaluation status

Evaluation is pending. No completed acceptance, speed, or quality results are included with this publication. The checkpoint has quantization provenance only; serving/runtime validation and the planned evaluation matrix have not completed.

Reproducibility

provenance/quantization/ includes the training and quantization commands, quantization manifest, calibration metadata where applicable, source scripts and patches, and the SHA-256 digest of the published drafter weights. Calibration prompt data is not redistributed.