Accelerating vision-language models with LFM2.5-VL-DSpark

Accelerating vision-language models with LFM2.5-VL-DSpark As with our recently released LFM2.5-DSpark drafter models , it adds a speculative decoding path that trades a minimal increase in memory footprint for a larger speedup without changing output quality. Faster inference: decode speedups up to 3.13x on device and 2.66x on an H100, with end-to-end gains up to 2.62x and 2.27x.

This PriceChange is relevant to the technology intelligence record because it involves Hugging Face, GitHub, Apple, OpenAI. The source article should remain the factual reference for follow-up coverage.

• As with our recently released LFM2.5-DSpark drafter models , it adds a speculative decoding path that trades a minimal increase in memory footprint for a larger speedup without changing output quality.
• Faster inference: decode speedups up to 3.13x on device and 2.66x on an H100, with end-to-end gains up to 2.62x and 2.27x.
• Small memory cost: the drafter adds 280M parameters, 8.9% on top of the 3B target Day-one support: LFM-compatible DSpark integrations for llama.cpp, MLX-VLM, and SGLang How does speculative decoding work for VLMs 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 representation before those layers, so the drafter operates on hidden-state vectors of identical dimensionality regardless of input modality.
• The inference algorithm is therefore unchanged from the text models.
• Training and Architecture We follow the DSpark recipe with a mixture of vision-language SFT data, weighted toward the workloads we expect the model to serve.