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 */
/*
* files.h - a file as OpenAI's API writes it (files.c), for the APIs that
* hand files back: uploads, batches.
*/
#ifndef JANAS_SERVER_FILES_H
#define JANAS_SERVER_FILES_H
#include <yyjson.h>
#include "files_store.h"
/* The File object of x, made in d. */
yyjson_mut_val *srv_file_json(yyjson_mut_doc *d, const struct srv_file *x);
#endif