This commit is contained in:
Johannes Gäßler
2026-03-06 10:16:05 +01:00
parent b90486e51d
commit 803d3a1964
2 changed files with 4 additions and 3 deletions
+2 -1
View File
@@ -185,6 +185,8 @@ if (NOT WIN32 OR NOT BUILD_SHARED_LIBS)
#llama_test(test-tokenizer-1-spm NAME test-tokenizer-1-baichuan ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-baichuan.gguf)
# llama_build_and_test(test-double-float.cpp) # SLOW
llama_build_and_test(test-llama-archs.cpp)
endif()
llama_build_and_test(test-chat-parser.cpp)
@@ -205,7 +207,6 @@ llama_build_and_test(
peg-parser/tests.h
)
llama_build_and_test(test-regex-partial.cpp)
llama_build_and_test(test-llama-archs.cpp)
if (NOT ${CMAKE_SYSTEM_PROCESSOR} MATCHES "s390x")
set(MODEL_NAME "tinyllamas/stories15M-q4_0.gguf")
+2 -2
View File
@@ -234,8 +234,8 @@ static std::pair<llama_model_ptr, llama_context_ptr> get_model_and_ctx(
llama_context_params ctx_params = llama_context_default_params();
ctx_params.n_ctx = 0;
ctx_params.n_threads = 1; // FIXME LLAMA_SANITIZE_THREAD workaround
ctx_params.n_threads_batch = 1;
ctx_params.n_threads = 4;
ctx_params.n_threads_batch = 4;
size_t tmp = seed;
llama_model_ptr model(llama_model_init_from_user(gguf_ctx, set_tensor_data, &tmp, model_params));