← Back to KHAO

Llama · AI Inference ·

Both configurations tap a DSpark block size of 9, a batch size of 1, and a temperature of 0

2 min read

Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.

★ Tier-1 Source

All three drafter models deliver noticeable throughput improvements on both the large-scale accelerator (H100) and the edge deployment (M4 Max MacBook).

Key facts

Summary

Faster inference: up to 3.18 throughput improvement on a GPU and up to 2.87x on-device. Toward on-device agentic inference: cuts function-calling latency by 57% on average for LFM2.5-2.6B. Day-one support for llama.cpp and SGLang: LFM-compatible DSpark integration is open-sourced upstream. The decode phase in LLM inference is traditionally memory-bound. Over the years, multiple approaches of speculation have been proposed, with the most prominent being EAGLE-3, DFlash, and, most recently, DSpark, which combines three components:.

Read full article at Hugging Face →

#Llama #AI Inference