owen/longhaul.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add portable CPU longhaul support

Browse Source
This commit is contained in:
Owen Qwen
2026-07-30 16:59:40 -05:00
parent a673afad85
commit d5458aa44e
11 changed files with 277 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-llama-archs.cpp
+18 -2
View File
@@ -9,6 +9,7 @@
// TODO: replace with #include "llama-ext.h" in the future
#include "../src/llama-arch.h"
#include "../src/llama-model.h"
#include "../src/llama-model-saver.h"
#include <cinttypes>
@@ -476,7 +477,9 @@ static int save_models(const llm_arch target_arch, const size_t seed, const ggml
if (!moe && moe_mandatory(arch)) {
continue;
}
if (!llama_model_saver_supports_arch(arch) || !arch_supported(arch)) {
const bool can_save_fixture =
llama_model_saver_supports_arch(arch) || arch == LLM_ARCH_LAGUNA;
if (!can_save_fixture || !arch_supported(arch)) {
LOG_INF("%s: %s model (%s) is unsupported, skipping\n", __func__, llm_arch_name(arch), moe ? "MoE" : "dense");
continue;
}
@@ -484,7 +487,20 @@ static int save_models(const llm_arch target_arch, const size_t seed, const ggml
auto model_and_ctx = get_model_and_ctx(gguf_ctx.get(), nullptr, seed, {});
const std::string path = dir + "/" + llm_arch_name(arch) + (moe ? "-moe.gguf" : "-dense.gguf");
LOG_INF("%s: Saving %s model (%s) to %s...\n", __func__, llm_arch_name(arch), moe ? "MoE" : "dense", path.c_str());
llama_model_save_to_file(model_and_ctx.first.get(), path.c_str());
if (llama_model_saver_supports_arch(arch)) {
llama_model_save_to_file(model_and_ctx.first.get(), path.c_str());
} else {
// Laguna is not supported by the production model saver yet.
// Preserve the exact synthetic fixture metadata and attach the
// initialized model tensors so longhaul can be tested from a
// real file without broadening the saver API.
gguf_context_ptr fixture(gguf_init_empty());
gguf_set_kv(fixture.get(), gguf_ctx.get());
for (const auto & item : llama_internal_get_tensor_map(model_and_ctx.first.get())) {
gguf_add_tensor(fixture.get(), item.second);
}
gguf_write_to_file(fixture.get(), path.c_str(), false);
}
}
}
llama_log_set(ud.original_logger.callback, ud.original_logger.user_data);