tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-12 19:37:53 -04:00
Code Issues Packages Projects Releases Wiki Activity

speculative : PoC for speeding-up inference via speculative sampling (#2926)

Browse Source 
* speculative : initial example

* speculative : print encoding speed

* speculative : add --draft CLI arg
This commit is contained in:
Georgi Gerganov
2023-09-03 15:12:08 +03:00
committed by GitHub
parent 8f429fa511
commit 47068e5170
6 changed files with 440 additions and 115 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/speculative/CMakeLists.txt Normal file
View File

@@ -0,0 +1,8 @@
set(TARGET speculative)
add_executable(${TARGET} speculative.cpp)
install(TARGETS ${TARGET} RUNTIME)
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
target_compile_features(${TARGET} PRIVATE cxx_std_11)
if(TARGET BUILD_INFO)
add_dependencies(${TARGET} BUILD_INFO)
endif()