LFM2.5-VL-DSparkを発表 ビジョン・ランゲージモデルにおける推測的デコードが導入されました
会社は、ビジョン・ランゲージモデル（VLM）LFM2.5-VL-3B用の実験的なDSparkドラフトモデルをリリースしました。このモデルは、CPUとGPUの両方で推論速度を向上させるために、speculative decodingを導入していますが、出力品質には影響を与えません。
01
根拠
- HHugging Face Blog企業開示2026-09-24 22:08
How does speculative decoding work for VLMs Training and Architecture Inference Speedup on CPU and GPU Limitations of speculation for vision workloads How to use LFM2.
- HHugging Face Blog企業開示2026-09-24 22:08
How does speculative decoding work for VLMs Training and Architecture Inference Speedup on CPU and GPU Limitations of speculation for vision workloads How to use LFM2.5-VL-DSpark Get Started Citation Today, we release an experimental DSpark draft model for our vision-language mo…
- HHugging Face Blog企業開示2026-09-24 22:08
The vision drafter uses the same architecture as our text LFM2.5-DSpark drafters: it captures the target model's hidden states at a fixed set of tapped layers and conditions on them to draft a block of k candidate tokens. Image patches and text tokens are projected into a shared…