Newest papers

Evaluating the Applicability of LLM Inference Optimizations on Apple Silicon

Kyrylo Yemets, Andrii Yaroshevych, Victor Muryn, Ostap Khomenko, Pavlo Kryven, Maksym Kmet, Maksym Shamrai, Mariya Hirna · 2026 · arXiv

DOI: 10.48550/arXiv.2610.31479 · open-access PDF

Indonesian

Apple Silicon adalah salah satu platform yang paling banyak digunakan untuk inferensi LLM lokal, namun hampir semua optimasi inferensi dirancang dan dikonfirmasi pada GPU NVIDIA kelas server di bawah beban kerja seragam. Optimasi mana yang mempertahankan manfaatnya ketika dipindahkan ke Apple Silicon, dan apa yang menentukan aplikasinya? Kami mengevaluasi empat keluarga optimasi: KV-cache pruning, speculative decoding, ported GPU kernels, dan post-training quantization.

Machine translation (Meta M2M100); the English original follows.

Abstract

Apple Silicon is among the most widely used platforms for local LLM inference, yet nearly all inference optimizations are designed and validated on server-class NVIDIA GPUs under batched serving workloads. Which optimizations retain their benefits when moved to Apple Silicon, and what determines their applicability? We evaluate four optimization families: KV-cache pruning, speculative decoding, ported GPU kernels, and post-training quantization. Experiments span four Apple machines under a common single-request decode workload, with matched RTX 4090 comparisons where possible. KV-cache pruning

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange