Packages

erllama

0.6.2
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 spacemit repack.h
Raw

c_src/llama.cpp/ggml/src/ggml-cpu/spacemit/repack.h 

#pragma once



#include "ggml-common.h"

#include "ggml.h"



#include <cstddef>

#include <cstdint>



namespace ggml::cpu::riscv64_spacemit {



template <typename BLOC_TYPE, int64_t INTER_SIZE, int64_t NB_COLS>

int repack(ggml_tensor * t, const void * data, size_t data_size);



}  // namespace ggml::cpu::riscv64_spacemit