Skip to content

llama : fix segfault from unknown model arch name #5820

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Mar 2, 2024
Merged

llama : fix segfault from unknown model arch name #5820

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3b257f8
llama : fix segfault from unknown model arch name
compilade Mar 1, 2024
6cf481b
llama : make all LLM maps const
compilade Mar 1, 2024
44e33d4
llama : remove redundant inner const for LLM_TENSOR_NAMES
compilade Mar 1, 2024
d8f7064
llama : remove redundant nullptr check in llm_arch_from_string
compilade Mar 2, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 16 additions & 15 deletions llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -215,7 +215,7 @@ enum llm_arch {
LLM_ARCH_UNKNOWN,
};

static std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
{ LLM_ARCH_LLAMA, "llama" },
{ LLM_ARCH_FALCON, "falcon" },
{ LLM_ARCH_GPT2, "gpt2" },
Expand All @@ -240,6 +240,7 @@ static std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
{ LLM_ARCH_MINICPM, "minicpm" },
{ LLM_ARCH_GEMMA, "gemma" },
{ LLM_ARCH_STARCODER2, "starcoder2" },
{ LLM_ARCH_UNKNOWN, "(unknown)" },
};

enum llm_kv {
Expand Down Expand Up @@ -300,7 +301,7 @@ enum llm_kv {
LLM_KV_TOKENIZER_RWKV,
};

static std::map<llm_kv, const char *> LLM_KV_NAMES = {
static const std::map<llm_kv, const char *> LLM_KV_NAMES = {
{ LLM_KV_GENERAL_ARCHITECTURE, "general.architecture" },
{ LLM_KV_GENERAL_QUANTIZATION_VERSION, "general.quantization_version" },
{ LLM_KV_GENERAL_ALIGNMENT, "general.alignment" },
Expand Down Expand Up @@ -364,7 +365,7 @@ struct LLM_KV {
llm_arch arch;

std::string operator()(llm_kv kv) const {
return ::format(LLM_KV_NAMES[kv], LLM_ARCH_NAMES[arch]);
return ::format(LLM_KV_NAMES.at(kv), LLM_ARCH_NAMES.at(arch));
}
};

Expand Down Expand Up @@ -399,7 +400,7 @@ enum llm_tensor {
LLM_TENSOR_LAYER_OUT_NORM,
};

static std::map<llm_arch, std::map<llm_tensor, std::string>> LLM_TENSOR_NAMES = {
static const std::map<llm_arch, std::map<llm_tensor, std::string>> LLM_TENSOR_NAMES = {
{
LLM_ARCH_LLAMA,
{
Expand Down Expand Up @@ -832,46 +833,46 @@ struct LLM_TN {
llm_arch arch;

std::string operator()(llm_tensor tensor) const {
if (LLM_TENSOR_NAMES[arch].find(tensor) == LLM_TENSOR_NAMES[arch].end()) {
if (LLM_TENSOR_NAMES.at(arch).find(tensor) == LLM_TENSOR_NAMES.at(arch).end()) {
return "__missing__";
}
return LLM_TENSOR_NAMES[arch].at(tensor);
return LLM_TENSOR_NAMES.at(arch).at(tensor);
}

std::string operator()(llm_tensor tensor, const std::string & suffix) const {
if (LLM_TENSOR_NAMES[arch].find(tensor) == LLM_TENSOR_NAMES[arch].end()) {
if (LLM_TENSOR_NAMES.at(arch).find(tensor) == LLM_TENSOR_NAMES.at(arch).end()) {
return "__missing__";
}
return LLM_TENSOR_NAMES[arch].at(tensor) + "." + suffix;
return LLM_TENSOR_NAMES.at(arch).at(tensor) + "." + suffix;
}

std::string operator()(llm_tensor tensor, int bid) const {
if (LLM_TENSOR_NAMES[arch].find(tensor) == LLM_TENSOR_NAMES[arch].end()) {
if (LLM_TENSOR_NAMES.at(arch).find(tensor) == LLM_TENSOR_NAMES.at(arch).end()) {
return "__missing__";
}
return ::format(LLM_TENSOR_NAMES[arch].at(tensor).c_str(), bid);
return ::format(LLM_TENSOR_NAMES.at(arch).at(tensor).c_str(), bid);
}

std::string operator()(llm_tensor tensor, const std::string & suffix, int bid) const {
if (LLM_TENSOR_NAMES[arch].find(tensor) == LLM_TENSOR_NAMES[arch].end()) {
if (LLM_TENSOR_NAMES.at(arch).find(tensor) == LLM_TENSOR_NAMES.at(arch).end()) {
return "__missing__";
}
return ::format(LLM_TENSOR_NAMES[arch].at(tensor).c_str(), bid) + "." + suffix;
return ::format(LLM_TENSOR_NAMES.at(arch).at(tensor).c_str(), bid) + "." + suffix;
}

std::string operator()(llm_tensor tensor, const std::string & suffix, int bid, int xid) const {
if (LLM_TENSOR_NAMES[arch].find(tensor) == LLM_TENSOR_NAMES[arch].end()) {
if (LLM_TENSOR_NAMES.at(arch).find(tensor) == LLM_TENSOR_NAMES.at(arch).end()) {
return "__missing__";
}
return ::format(LLM_TENSOR_NAMES[arch].at(tensor).c_str(), bid, xid) + "." + suffix;
return ::format(LLM_TENSOR_NAMES.at(arch).at(tensor).c_str(), bid, xid) + "." + suffix;
}
};

//
// gguf helpers
//

static std::map<int32_t, const char *> LLAMA_ROPE_SCALING_TYPES = {
static const std::map<int32_t, const char *> LLAMA_ROPE_SCALING_TYPES = {
{ LLAMA_ROPE_SCALING_TYPE_NONE, "none" },
{ LLAMA_ROPE_SCALING_TYPE_LINEAR, "linear" },
{ LLAMA_ROPE_SCALING_TYPE_YARN, "yarn" },
Expand Down