Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.clang-tidy
#	.devops/musa.Dockerfile
#	.github/workflows/build-linux-cross.yml
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	.gitignore
#	CODEOWNERS
#	CONTRIBUTING.md
#	README.md
#	build-xcframework.sh
#	ci/README-MUSA.md
#	ci/run.sh
#	common/CMakeLists.txt
#	docs/docker.md
#	examples/CMakeLists.txt
#	examples/eval-callback/CMakeLists.txt
#	examples/model-conversion/Makefile
#	examples/model-conversion/README.md
#	examples/model-conversion/logits.cpp
#	examples/model-conversion/scripts/causal/compare-logits.py
#	examples/model-conversion/scripts/causal/run-org-model.py
#	examples/model-conversion/scripts/embedding/compare-embeddings-logits.sh
#	examples/model-conversion/scripts/embedding/run-converted-model.sh
#	examples/model-conversion/scripts/embedding/run-original-model.py
#	examples/model-conversion/scripts/utils/check-nmse.py
#	examples/model-conversion/scripts/utils/inspect-org-model.py
#	examples/model-conversion/scripts/utils/semantic_check.py
#	ggml/CMakeLists.txt
#	ggml/include/ggml-zdnn.h
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/set_rows.cl
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/set_rows.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-zdnn/ggml-zdnn.cpp
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-quantize-perf.cpp
#	tests/test-tokenizers-repo.sh
#	tools/perplexity/perplexity.cpp
#	tools/server/tests/README.md
This commit is contained in:
Concedo
2025-09-27 17:09:14 +08:00
112 changed files with 10916 additions and 4106 deletions
+22 -6
View File
@@ -22,6 +22,7 @@
#include <climits>
#include <cmath>
#include <codecvt>
#include <chrono>
#include <cstdarg>
#include <cstring>
#include <ctime>
@@ -58,6 +59,11 @@
#include <unistd.h>
#endif
#if defined(__linux__)
#include <sys/types.h>
#include <pwd.h>
#endif
#if defined(_MSC_VER)
#pragma warning(disable: 4244 4267) // possible loss of data
#endif
@@ -872,8 +878,20 @@ std::string fs_get_cache_directory() {
#if defined(__linux__) || defined(__FreeBSD__) || defined(_AIX) || defined(__OpenBSD__)
if (std::getenv("XDG_CACHE_HOME")) {
cache_directory = std::getenv("XDG_CACHE_HOME");
} else {
} else if (std::getenv("HOME")) {
cache_directory = std::getenv("HOME") + std::string("/.cache/");
} else {
#if defined(__linux__)
/* no $HOME is defined, fallback to getpwuid */
struct passwd *pw = getpwuid(getuid());
if ((!pw) || (!pw->pw_dir)) {
throw std::runtime_error("Failed to find $HOME directory");
}
cache_directory = std::string(pw->pw_dir) + std::string("/.cache/");
#else /* defined(__linux__) */
throw std::runtime_error("Failed to find $HOME directory");
#endif /* defined(__linux__) */
}
#elif defined(__APPLE__)
cache_directory = std::getenv("HOME") + std::string("/Library/Caches/");
@@ -968,15 +986,13 @@ struct common_init_result common_init_from_params(common_params & params) {
bool has_eos = llama_vocab_eos(vocab) != LLAMA_TOKEN_NULL;
bool has_sep = llama_vocab_sep(vocab) != LLAMA_TOKEN_NULL;
bool has_rerank_prompt = llama_model_chat_template(model, "rerank") != NULL;
if (!has_eos && !has_sep) {
LOG_WRN("%s: warning: vocab does not have an EOS token or SEP token, reranking will not work\n", __func__);
if (!has_eos && !has_sep && !has_rerank_prompt) {
LOG_WRN("%s: warning: vocab does not have an EOS token, SEP token, or rerank prompt. Reranking will not work\n", __func__);
ok = false;
} else if (!has_eos) {
LOG_WRN("%s: warning: vocab does not have an EOS token, using SEP token as fallback\n", __func__);
} else if (!has_sep) {
LOG_WRN("%s: warning: vocab does not have a SEP token, reranking will not work\n", __func__);
ok = false;
}
if (!ok) {