vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Deduplicate q4 quantization functions (#383)

Browse source 
* Deduplicate q4 quantization functions

* Use const; add basic test

* Re-enable quantization test

* Disable AVX2 flags in CI

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Stephan Walter 2023-03-22 17:29:06 +00:00 • committed by GitHub
parent 97940520e8
commit 69c92298a9
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 119 additions and 113 deletions
Download patch file Download diff file Expand all files Collapse all files

13
tests/CMakeLists.txt
View file

@ -1,4 +1,9 @@
set(TEST_TARGET test-tokenizer-0)
add_executable(${TEST_TARGET} ${TEST_TARGET}.cpp)
target_link_libraries(${TEST_TARGET} PRIVATE llama ggml utils)
add_test(NAME ${TEST_TARGET} COMMAND $<TARGET_FILE:${TEST_TARGET}> ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab.bin)
function(llama_add_test source)
get_filename_component(TEST_TARGET ${source} NAME_WE)
add_executable(${TEST_TARGET} ${source})
target_link_libraries(${TEST_TARGET} PRIVATE llama ggml utils)
add_test(NAME ${TEST_TARGET} COMMAND $<TARGET_FILE:${TEST_TARGET}> ${ARGN})
endfunction()
llama_add_test(test-quantize.c)
llama_add_test(test-tokenizer-0.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab.bin)