AI article

Up to 3.2x Faster Inference with LFM2.5-DSpark

No preview is available. Read the original article for the full story.

huggingface | Aug 20, 2026 | xx, Leonie Monigatti, Fernando Fernandes Neto, Tarek Dakhran, nathan ranchin

Automated excerpt

Today, we release DSpark draft model checkpoints for three models from our LFM2. 5 family: LFM2. 5-1. 2B-Instruct, LFM2. 5-2. 6B, and LFM2. 5-8B-A1B. Under greedy decoding, a draft token is only accepted if it matches the target model’s distribution. Running the DSpark draft models with SGLang requires an SGLang build with DSpark support for LFM2 targets (PR #31041).

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.

Read the original article

More AI news