--- title: "Up to 3.2x Faster Inference with LFM2.5-DSpark" url: https://daily.dev/posts/up-to-3-2x-faster-inference-with-lfm2-5-dspark-nwilr6rly source_url: https://huggingface.co/blog/LiquidAI/lfm25-dspark type: article source: "Hugging Face" published: 2026-08-20T16:54:46.570Z updated: 2026-08-20T16:55:13.642Z tags: ["local-ai", "ai-inference", "llama-cpp"] reading_time: 6 upvotes: 0 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Up to 3.2x Faster Inference with LFM2.5-DSpark **[Hugging Face](https://daily.dev/sources/huggingface)** · 6 min read · 0 upvotes · 0 comments ## Summary Liquid AI released DSpark draft model checkpoints for its LFM2.5 family (1.2B-Instruct, 2.6B, and 8B-A1B), adding a speculative decoding path that speeds up inference without changing output quality. DSpark combines a DFlash-style parallel backbone, a lightweight Markov-chain sequential head, and a confidence-scheduled verifier. Reported gains include up to 3.18x throughput on H100 GPUs and up to 2.87x on an M4 Max MacBook via llama.cpp Metal, plus a 57% average cut in function-calling latency for LFM2.5-2.6B. Since verification guarantees output identical to baseline greedy decoding, benchmark accuracy is unchanged. Day-one support ships for llama.cpp and SGLang, with checkpoints available in Safetensors and GGUF formats, and integration code open-sourced upstream. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What speedup does DSpark speculative decoding give for LFM2.5-2.6B inference? DSpark draft model checkpoints deliver up to 3.18x throughput improvement on an H100 GPU and up to 2.87x on-device speedup, with LFM2.5-2.6B averaging a 2.67x speedup on H100 and 2.27x on an M4 Max MacBook Pro across five benchmarks (MATH500, HumanEval, MBPP, GSM8K, MT-Bench). It also cuts function-calling latency by 57% on average, while output remains identical to baseline greedy decoding. _Engineers optimizing LLM serving costs can track speculative decoding advances like this via daily.dev._ ### Does speculative decoding with DSpark change LLM output quality or accuracy? No, output quality is unchanged because DSpark speculative decoding under greedy decoding only accepts a draft token if it matches the target model's distribution; rejected tokens are replaced by the target model's own token. The emitted sequence is therefore identical to baseline greedy decoding by construction, so benchmark accuracy such as pass@1 or exact match stays the same. _Anyone evaluating whether a speedup trades away accuracy can verify these trade-offs on daily.dev._ ### How do I run LFM2.5-2.6B with DSpark speculative decoding in SGLang? Launch SGLang with the target model path set to LiquidAI/LFM2.5-2.6B, set --speculative-algorithm to DSPARK, point --speculative-draft-model-path to LiquidAI/LFM2.5-2.6B-DSpark, use flashinfer as the draft attention backend, and disable the radix cache with --disable-radix-cache --mem-fraction-static 0.75. This requires an SGLang build with DSpark support for LFM2 targets from PR #31041. _Developers wiring up speculative decoding configs can find setup details like this through daily.dev._ ## Similar posts on daily.dev - [Researchers Found a Way to Make LLMs 8.5x Faster\!](https://daily.dev/posts/researchers-found-a-way-to-make-llms-8-5x-faster--gy4vk6zg4) · Daily Dose of Data Science \| Avi Chawla \| Substack · 0 upvotes · 0 comments --- Tags: [#local-ai](https://daily.dev/tags/local-ai), [#ai-inference](https://daily.dev/tags/ai-inference), [#llama-cpp](https://daily.dev/tags/llama-cpp) [View this post on daily.dev](https://daily.dev/posts/up-to-3-2x-faster-inference-with-lfm2-5-dspark-nwilr6rly)