Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/full.Dockerfile
#	.devops/main-cuda.Dockerfile
#	.devops/main-rocm.Dockerfile
#	.devops/main-vulkan.Dockerfile
#	.devops/main.Dockerfile
#	.devops/server-cuda.Dockerfile
#	.devops/server.Dockerfile
#	README.md
#	common/CMakeLists.txt
#	grammars/README.md
#	tests/test-grammar-integration.cpp
#	tests/test-grammar-parser.cpp
#	tests/test-json-schema-to-grammar.cpp
This commit is contained in:
Concedo 2024-06-09 17:30:05 +08:00
commit 562d980140
25 changed files with 881 additions and 676 deletions

View file

@ -62,10 +62,10 @@ static size_t split_str_to_n_bytes(std::string str) {
int n;
if (str.back() == 'M') {
sscanf(str.c_str(), "%d", &n);
n_bytes = (size_t)n * 1024 * 1024; // megabytes
n_bytes = (size_t)n * 1000 * 1000; // megabytes
} else if (str.back() == 'G') {
sscanf(str.c_str(), "%d", &n);
n_bytes = (size_t)n * 1024 * 1024 * 1024; // gigabytes
n_bytes = (size_t)n * 1000 * 1000 * 1000; // gigabytes
} else {
throw std::invalid_argument("error: supported units are M (megabytes) or G (gigabytes), but got: " + std::string(1, str.back()));
}
@ -285,7 +285,7 @@ struct split_strategy {
struct ggml_tensor * t = ggml_get_tensor(ctx_meta, gguf_get_tensor_name(ctx_out, i));
total_size += ggml_nbytes(t);
}
total_size = total_size / 1024 / 1024; // convert to megabytes
total_size = total_size / 1000 / 1000; // convert to megabytes
printf("split %05d: n_tensors = %d, total_size = %ldM\n", i_split + 1, gguf_get_n_tensors(ctx_out), total_size);
i_split++;
}