tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-04 18:16:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

Introduce C-style API (#370)

Browse Source 
* Major refactoring - introduce C-style API

* Clean up

* Add <cassert>

* Add <iterator>

* Add <algorithm> ....

* Fix timing reporting and accumulation

* Measure eval time only for single-token calls

* Change llama_tokenize return meaning
This commit is contained in:
Georgi Gerganov
2023-03-22 07:32:36 +02:00
committed by GitHub
parent da0e9fe90c
commit f5a77a629b
14 changed files with 1954 additions and 1752 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/CMakeLists.txt
View File

@ -1,4 +1,4 @@
set(TEST_TARGET test-tokenizer-0)
add_executable(${TEST_TARGET} ${TEST_TARGET}.cpp)
target_link_libraries(${TEST_TARGET} PRIVATE utils)
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)