llama : fix segfault from unknown model arch name (#5820)

* llama : fix segfault from unknown model arch name

* llama : make all LLM maps const

This also requires using `std::map::at` instead of its `operator[]`
which does not exist for const maps.

* llama : name LLM_ARCH_UNKNOWN to "(unknown)"

This avoids errors from `std::map::at` when
getting the general name of the model architecture.
Using "(unknown)" instead of an empty string as per suggestion
https://github.com/ggerganov/llama.cpp/pull/5820#issuecomment-1973735284

* llama : remove redundant inner const for LLM_TENSOR_NAMES

The extra const won't do anything here as const maps
return const references to values.

Co-authored-by: Jared Van Bortel <redacted>
* llama : remove redundant nullptr check in llm_arch_from_string

Since LLM_ARCH_NAMES is a const map, no spurious elements
with a NULL name are inserted anymore, so this check is dead code.

---------

Co-authored-by: Jared Van Bortel <redacted>

diff --git a/llama.cpp b/llama.cpp
index cb6266a433ed57b3c9cb613efc23f31e1f01dc32..790c2740fba19758f7f2f79204156391a4941229 100644 (file)
--- a/llama.cpp
+++ b/llama.cpp
@@ -216,7 +216,7 @@ 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"       },
@@ -241,6 +241,7 @@ 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 {
@@ -301,7 +302,7 @@ 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"                     },
@@ -365,7 +366,7 @@ 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));
     }
 };
 
@@ -400,7 +401,7 @@ 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,
         {
@@ -833,38 +834,38 @@ 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;
     }
 };
 
@@ -872,7 +873,7 @@ struct LLM_TN {
 // 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"   },