37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
C avx2ccpu-inferenceggufinference-enginelinuxllmlocal-llmmixture-of-expertsmoenvmequantizationqwen3simdspeculative-decodingvulkan
/* SPDX-License-Identifier: GPL-3.0-or-later
Copyright (C) 2026 Maurizio Cammalleri */
#version 450
// y[i] = fma(a, b, c) of n triples (gpu_fma.c: whether this driver rounds
// fma() once, as the CPU does).
#extension GL_EXT_buffer_reference : require
#extension GL_EXT_buffer_reference_uvec2 : require
layout(local_size_x = 64) in;
layout(buffer_reference, std430, buffer_reference_align = 4) readonly buffer F { float v[]; };
layout(buffer_reference, std430, buffer_reference_align = 4) writeonly buffer FO { float v[]; };
layout(push_constant) uniform P { uvec2 abc, y; uint n; } p;
void main()
{
uint i = gl_GlobalInvocationID.x;
if (i >= p.n)
return;
F t = F(p.abc);
FO(p.y).v[i] = fma(t.v[3u * i], t.v[3u * i + 1u], t.v[3u * i + 2u]);
}