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

batched : add bench tool (#3545)

Browse source 
* batched : add bench tool

* batched : minor fix table

* batched-bench : add readme + n_kv_max is now configurable

* batched-bench : init warm-up batch

* batched-bench : pass custom set of PP, TG and PL

* batched-bench : add mmq CLI arg
This commit is contained in:
Georgi Gerganov 2023-10-11 21:25:33 +03:00 • committed by GitHub
parent 24ba3d829e
commit 8c70a5ff25
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 321 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

5
examples/batched-bench/CMakeLists.txt Normal file
View file

@ -0,0 +1,5 @@
set(TARGET batched-bench)
add_executable(${TARGET} batched-bench.cpp)
install(TARGETS ${TARGET} RUNTIME)
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
target_compile_features(${TARGET} PRIVATE cxx_std_11)