Real bench on your Mac: llama-bench -m ~/.xariv/relay/models/Llama-3.2-1B-Instruct-Q4_K_M.gguf -p 128 -n 64 vs GGML_METAL_FUSION_DISABLE=1. Relay deploy

XARIV Fusion Studio

One decode step. Hundreds of kernels vs a dozen fused blocks.

Pick a cached Llama 3.2 1B GGUF and replay how llama.cpp Metal fusion collapses micro-ops into fewer GPU launches — the same idea as our kernel fusion study, scaled down for edge inference.

Illustrative replay (not a live Metal trace). Timings are scaled from local llama-bench on Apple Silicon with fusion on vs GGML_METAL_FUSION_DISABLE=1. Real weights live in ~/.xariv/relay/models/.

Left · unfused

Fusion disabled

GGML_METAL_FUSION_DISABLE=1 — every micro-op launches separately

Right · fused

Metal fusion ON

Default llama.cpp — fused RMSNorm·RoPE·QKV, attn epilogues

Fusion disabled

432 launches · target 17.4 ms / step

Launched

/ 432

Launch overhead

Step time

tok/s

57.6

Kernel timeline

fusedmatmulattnnormview/reshape
Kernel launch log appears here…

Metal fusion ON

176 launches · target 15.5 ms / step

Launched

/ 176

Launch overhead

Step time

tok/s

64.6

Kernel timeline

fusedmatmulattnnormview/reshape
Kernel launch log appears here…