Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/llama-cli-cuda.Dockerfile
#	.devops/llama-server-cuda.Dockerfile
#	.devops/llama-server-intel.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.devops/llama-server-vulkan.Dockerfile
#	.devops/llama-server.Dockerfile
#	.github/workflows/docker.yml
#	docs/docker.md
#	examples/llama-bench/llama-bench.cpp
#	flake.lock
#	ggml/include/ggml.h
#	ggml/src/CMakeLists.txt
#	scripts/sync-ggml.last
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-grad0.cpp
#	tests/test-rope.cpp
This commit is contained in:
Concedo 2024-08-30 10:37:39 +08:00
commit d220495dd4
42 changed files with 100585 additions and 99448 deletions

View file

@ -2535,8 +2535,8 @@ int main(int argc, char ** argv) {
});
LOG_INFO("system info", {
{"n_threads", params.n_threads},
{"n_threads_batch", params.n_threads_batch},
{"n_threads", params.cpuparams.n_threads},
{"n_threads_batch", params.cpuparams_batch.n_threads},
{"total_threads", std::thread::hardware_concurrency()},
{"system_info", llama_print_system_info()},
});
@ -2573,7 +2573,7 @@ int main(int argc, char ** argv) {
auto res_error = [](httplib::Response & res, json error_data) {
json final_response {{"error", error_data}};
res.set_content(final_response.dump(), MIMETYPE_JSON);
res.set_content(final_response.dump(-1, ' ', false, json::error_handler_t::replace), MIMETYPE_JSON);
res.status = json_value(error_data, "code", 500);
};