llama-cpp-turboquant/tools/CMakeLists.txt
Johannes Gäßler b1f3a6e5db
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)
* llama: automatically fit args to free memory

llama-fit-params tool

* fix CI

* hints for bug reports, ensure no reallocation

* fix segfault with Vulkan

* add llama-fit-params to CI

* fix CI

* fix CI

* fix CI

* minor adjustments

* fix assignment of 1 dense layer

* fix logger not being reset on model load failure

* remove --n-gpu-layer hint on model load failure

* fix llama-fit-params verbosity

* fix edge case

* fix typo [no ci]
2025-12-15 09:24:59 +01:00

41 lines
893 B
CMake

# dependencies
find_package(Threads REQUIRED)
# third-party
# ...
# flags
llama_add_compile_flags()
# tools
if (EMSCRIPTEN)
else()
add_subdirectory(batched-bench)
add_subdirectory(gguf-split)
add_subdirectory(imatrix)
add_subdirectory(llama-bench)
add_subdirectory(cli)
add_subdirectory(completion)
add_subdirectory(perplexity)
add_subdirectory(quantize)
if (LLAMA_BUILD_SERVER)
add_subdirectory(server)
endif()
add_subdirectory(run)
add_subdirectory(tokenize)
add_subdirectory(tts)
add_subdirectory(mtmd)
if (GGML_RPC)
add_subdirectory(rpc)
endif()
if (NOT GGML_BACKEND_DL)
# these examples use the backends directly and cannot be built with dynamic loading
add_subdirectory(cvector-generator)
add_subdirectory(export-lora)
endif()
add_subdirectory(fit-params)
endif()