llama-cpp-sys-4 0.2.46

Low Level Bindings to llama.cpp
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67

cmake_minimum_required(VERSION 3.22.2)
project(ggml-htp C CXX ASM)

include(${HEXAGON_SDK_ROOT}/build/cmake/hexagon_fun.cmake)

include_directories(
    ${HEXAGON_SDK_ROOT}/incs
    ${HEXAGON_SDK_ROOT}/incs/stddef
    ${CMAKE_CURRENT_SOURCE_DIR}/../../../include
    ${CMAKE_CURRENT_SOURCE_DIR}/../..
    ${CMAKE_CURRENT_SOURCE_DIR}/..
    ${CMAKE_CURRENT_SOURCE_DIR}
    ${CMAKE_CURRENT_BINARY_DIR})

set(HTP_LIB ggml-htp-${DSP_VERSION})

add_library(${HTP_LIB} SHARED
    main.c
    htp_iface_skel.c
    worker-pool.c
    hex-dma.c
    matmul-ops.c
    binary-ops.c
    unary-ops.c
    sum-rows-ops.c
    softmax-ops.c
    act-ops.c
    rope-ops.c
    flash-attn-ops.c
    set-rows-ops.c
    get-rows-ops.c
    cpy-ops.c
    repeat-ops.c
    argsort-ops.c
    ssm-conv.c
    cumsum-ops.c
)

target_compile_definitions(${HTP_LIB} PRIVATE
    $<IF:$<BOOL:${HEXAGON_HTP_DEBUG}>,HTP_DEBUG=1,NDEBUG=1>
    $<IF:$<BOOL:${HEXAGON_HTP_DEBUG}>,FARF_HIGH=1,>
    FP32_QUANTIZE_GROUP_SIZE=${GGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE})

# HMX acceleration: available on v73+ architectures
set(HTP_HMX_VERSIONS v73 v75 v79 v81)
list(FIND HTP_HMX_VERSIONS ${DSP_VERSION} _hmx_idx)

if (_hmx_idx GREATER_EQUAL 0)
    target_sources(${HTP_LIB} PRIVATE
        hmx-queue.c
        hmx-matmul-ops.c
    )

    # -mhmx enables HMX instruction set (needed by files that include hmx-utils.h)
    set_source_files_properties(
        hmx-matmul-ops.c
        PROPERTIES COMPILE_OPTIONS "-mhmx"
    )

    target_compile_definitions(${HTP_LIB} PRIVATE HTP_HAS_HMX=1)
endif()

build_idl(htp_iface.idl ${HTP_LIB})

set_target_properties(${HTP_LIB} PROPERTIES EXPORT_COMPILE_COMMANDS ON)

install(TARGETS ${HTP_LIB})