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

all : be more strict about converting float to double (#458)

Browse source 
* Be more strict about converting float to double

* Test equivalence of round, SILU implementations

Test module is commented out in CMakeLists.txt because the tests may
take a long time, depending on how much the compiler optimizes.

* Fix softmax in perplexity.cpp

* all : prefer float over double where appropriate

* perplexity : add <cmath>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Stephan Walter 2023-03-28 16:48:20 +00:00 • committed by GitHub
parent 20e1e84884
commit 436e561931
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
11 changed files with 185 additions and 117 deletions
Download patch file Download diff file Expand all files Collapse all files

1
tests/CMakeLists.txt
View file

@ -5,5 +5,6 @@ function(llama_add_test source)
add_test(NAME ${TEST_TARGET} COMMAND $<TARGET_FILE:${TEST_TARGET}> ${ARGN})
endfunction()
# llama_add_test(test-double-float.c) # SLOW
llama_add_test(test-quantize.c)
llama_add_test(test-tokenizer-0.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab.bin)