Packages

erllama

0.2.0
0.8.0 retired 0.7.0 retired 0.6.2 retired 0.6.1 retired 0.6.0 retired 0.5.1 retired 0.5.0 retired 0.4.0 retired 0.3.0 retired 0.2.0 retired 0.1.2 retired 0.1.1 retired 0.1.0 retired

Native Erlang/OTP wrapper around llama.cpp with token-exact tiered KV cache; cache more warm state than fits in RAM

Retired package: Renamed - Renamed to barrel_inference: https://github.com/barrel-platform/barrel_inference
HexDocs

Current section

Files

Jump to
Readme
13 Versions
0 Dependencies
Dependants
Files
Activity
erllama c_src llama.cpp ggml src ggml-cpu amx mmq.h
Raw

c_src/llama.cpp/ggml/src/ggml-cpu/amx/mmq.h 

#pragma once

#include "common.h"



size_t ggml_backend_amx_desired_wsize(const struct ggml_tensor * dst);



size_t ggml_backend_amx_get_alloc_size(const struct ggml_tensor * tensor);



void ggml_backend_amx_convert_weight(struct ggml_tensor * tensor, const void * data, size_t offset, size_t size);



void ggml_backend_amx_mul_mat(const struct ggml_compute_params * params, struct ggml_tensor * dst);