mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-01-26 17:20:01 +00:00
519405dc97
* WIP: absorb adding input into std_attn and std_ffn * WIP: NCCL infra * WIP: add reduce and fake_cpy ops * WIP * WIP: graph appears to work, layer is broken * WIP: Qwen3-MoE works with graph, layer still broken * WIP: GLM-4.5 graph works * WIP: fix sm layer (dense) * WIP: fix sm layer (MoE) * WIP: fast PP with bespoke 4-GPU NCCL I guess, I'm not using NCCL the right way as PP is very low with a single communicator group for 3 or more GPUs. But if I create 4 communicator groups for pairs of GPUs (0,1, 2,3, 0,2, 1,3) and use that, PP is fast: I'm hitting 1500 t/s for L3-70B on the 4x3090 system, which is ~20% better than the previous sm graph without NCCL. But that cannot be the solution (I cannot be creating pairwise communicators and associated logic for every possible number of GPUs). * WIP: Cohere2 * Explicitely set device * Bespoke 3-GPU case * WIP * Do not repeat get_rows multiple times * Fix 3 GPUs * OK, let's leave it in * Simple async * This sync seems enough * Only do async for 4 or more backends With 2 GPUs (so, 3 backends) not using async is slightly faster * Scheduler changes * Use OpenMP if available Surprisingly (at least to me), this is quite a bit faster than std::thread and std::barrier. GLM-4.5-AIR with 4 GPUs is now at 105 t/s at zero context! * Do not use OpenMP if there are tensor overrides * Set omp max active levels * Be more careful with having set the device before using a stream * Command line option to turn on async. Set to false by defualt for now --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
146 lines
7.4 KiB
CMake
146 lines
7.4 KiB
CMake
function(llama_test target)
|
|
include(CMakeParseArguments)
|
|
set(options)
|
|
set(oneValueArgs NAME LABEL WORKING_DIRECTORY)
|
|
set(multiValueArgs ARGS)
|
|
cmake_parse_arguments(LLAMA_TEST "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
|
|
|
|
if (NOT DEFINED LLAMA_TEST_LABEL)
|
|
set(LLAMA_TEST_LABEL "main")
|
|
endif()
|
|
if (NOT DEFINED LLAMA_TEST_WORKING_DIRECTORY)
|
|
set(LLAMA_TEST_WORKING_DIRECTORY .)
|
|
endif()
|
|
if (DEFINED LLAMA_TEST_NAME)
|
|
set(TEST_NAME ${LLAMA_TEST_NAME})
|
|
else()
|
|
set(TEST_NAME ${target})
|
|
endif()
|
|
|
|
set(TEST_TARGET ${target})
|
|
|
|
add_test(
|
|
NAME ${TEST_NAME}
|
|
WORKING_DIRECTORY ${LLAMA_TEST_WORKING_DIRECTORY}
|
|
COMMAND $<TARGET_FILE:${TEST_TARGET}>
|
|
${LLAMA_TEST_ARGS})
|
|
|
|
set_property(TEST ${TEST_NAME} PROPERTY LABELS ${LLAMA_TEST_LABEL})
|
|
endfunction()
|
|
|
|
# Builds and runs a test source file.
|
|
# Optional args:
|
|
# - NAME: name of the executable & test target (defaults to the source file name without extension)
|
|
# - LABEL: label for the test (defaults to main)
|
|
# - ARGS: arguments to pass to the test executable
|
|
# - WORKING_DIRECTORY
|
|
function(llama_target_and_test source)
|
|
include(CMakeParseArguments)
|
|
set(options)
|
|
set(oneValueArgs NAME LABEL WORKING_DIRECTORY)
|
|
set(multiValueArgs ARGS)
|
|
cmake_parse_arguments(LLAMA_TEST "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
|
|
|
|
if (NOT DEFINED LLAMA_TEST_LABEL)
|
|
set(LLAMA_TEST_LABEL "main")
|
|
endif()
|
|
if (NOT DEFINED LLAMA_TEST_WORKING_DIRECTORY)
|
|
set(LLAMA_TEST_WORKING_DIRECTORY .)
|
|
endif()
|
|
if (DEFINED LLAMA_TEST_NAME)
|
|
set(TEST_TARGET ${LLAMA_TEST_NAME})
|
|
else()
|
|
get_filename_component(TEST_TARGET ${source} NAME_WE)
|
|
endif()
|
|
|
|
add_executable(${TEST_TARGET} ${source} get-model.cpp)
|
|
install(TARGETS ${TEST_TARGET} RUNTIME)
|
|
target_link_libraries(${TEST_TARGET} PRIVATE common)
|
|
add_test(
|
|
NAME ${TEST_TARGET}
|
|
WORKING_DIRECTORY ${LLAMA_TEST_WORKING_DIRECTORY}
|
|
COMMAND $<TARGET_FILE:${TEST_TARGET}>
|
|
${LLAMA_TEST_ARGS})
|
|
|
|
set_property(TEST ${TEST_TARGET} PROPERTY LABELS ${LLAMA_TEST_LABEL})
|
|
endfunction()
|
|
|
|
# build test-tokenizer-0 target once and add many tests
|
|
add_executable(test-tokenizer-0 test-tokenizer-0.cpp)
|
|
target_link_libraries(test-tokenizer-0 PRIVATE common)
|
|
install(TARGETS test-tokenizer-0 RUNTIME)
|
|
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-bert-bge ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-bert-bge.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-command-r ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-command-r.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-deepseek-coder ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-deepseek-coder.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-deepseek-llm ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-deepseek-llm.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-falcon ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-falcon.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-gpt-2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-2.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-bpe ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-bpe.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-spm ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-spm.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-mpt ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-mpt.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-phi-3 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-phi-3.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-qwen2.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-starcoder.gguf)
|
|
|
|
if (LLAMA_LLGUIDANCE)
|
|
llama_target_and_test(test-grammar-llguidance.cpp ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-bpe.gguf)
|
|
endif ()
|
|
|
|
if (NOT WIN32)
|
|
# these tests are disabled on Windows because they use internal functions not exported with LLAMA_API
|
|
#llama_target_and_test(test-sampling.cpp)
|
|
#llama_target_and_test(test-grammar-parser.cpp)
|
|
#llama_target_and_test(test-grammar-integration.cpp)
|
|
#llama_target_and_test(test-llama-grammar.cpp)
|
|
#llama_target_and_test(test-chat.cpp)
|
|
# TODO: disabled on loongarch64 because the ggml-ci node lacks Python 3.8
|
|
if (NOT ${CMAKE_SYSTEM_PROCESSOR} MATCHES "loongarch64")
|
|
llama_target_and_test(test-json-schema-to-grammar.cpp WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/..)
|
|
target_include_directories(test-json-schema-to-grammar PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/../examples/server)
|
|
endif()
|
|
|
|
|
|
# build test-tokenizer-1-bpe target once and add many tests
|
|
add_executable(test-tokenizer-1-bpe test-tokenizer-1-bpe.cpp)
|
|
target_link_libraries(test-tokenizer-1-bpe PRIVATE common)
|
|
install(TARGETS test-tokenizer-1-bpe RUNTIME)
|
|
|
|
# TODO: disabled due to slowness
|
|
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-aquila ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-aquila.gguf)
|
|
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-falcon ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-falcon.gguf)
|
|
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-gpt-2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-2.gguf)
|
|
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-gpt-neox ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-neox.gguf)
|
|
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-llama-bpe ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-bpe.gguf --ignore-merges)
|
|
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-mpt ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-mpt.gguf)
|
|
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-refact ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf)
|
|
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-starcoder ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-starcoder.gguf)
|
|
|
|
# build test-tokenizer-1-spm target once and add many tests
|
|
add_executable(test-tokenizer-1-spm test-tokenizer-1-spm.cpp)
|
|
target_link_libraries(test-tokenizer-1-spm PRIVATE common)
|
|
install(TARGETS test-tokenizer-1-spm RUNTIME)
|
|
|
|
llama_test(test-tokenizer-1-spm NAME test-tokenizer-1-llama-spm ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-spm.gguf)
|
|
#llama_test(test-tokenizer-1-spm NAME test-tokenizer-1-baichuan ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-baichuan.gguf)
|
|
|
|
# llama_target_and_test(test-double-float.cpp) # SLOW
|
|
endif()
|
|
|
|
llama_target_and_test(test-chat-parser.cpp)
|
|
#llama_target_and_test(test-chat-template.cpp)
|
|
llama_target_and_test(test-json-partial.cpp)
|
|
llama_target_and_test(test-regex-partial.cpp)
|
|
|
|
# llama_target_and_test(test-opt.cpp) # SLOW
|
|
|
|
llama_target_and_test(test-model-load-cancel.cpp LABEL "model")
|
|
llama_target_and_test(test-autorelease.cpp LABEL "model")
|
|
|
|
|
|
# dummy executable - not installed
|
|
get_filename_component(TEST_TARGET test-c.c NAME_WE)
|
|
add_executable(${TEST_TARGET} test-c.c)
|
|
target_link_libraries(${TEST_TARGET} PRIVATE llama)
|