vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge remote-tracking branch 'origin/master' into sl/custom-tensor-offload

Browse source
This commit is contained in:
slaren 2025-02-02 17:18:30 +01:00
commit bb6b97e71e
122 changed files with 9807 additions and 1102 deletions
Download patch file Download diff file Expand all files Collapse all files

20
common/common.h
View file

@ -4,6 +4,7 @@
#include "llama-cpp.h"
#include <set>
#include <string>
#include <vector>
#include <sstream>
@ -109,6 +110,11 @@ enum common_conversation_mode {
COMMON_CONVERSATION_MODE_AUTO = 2,
};
struct common_grammar_trigger {
std::string word;
bool at_start;
};
// sampling parameters
struct common_params_sampling {
uint32_t seed = LLAMA_DEFAULT_SEED; // the seed used to initialize llama_sampler
@ -154,7 +160,11 @@ struct common_params_sampling {
COMMON_SAMPLER_TYPE_TEMPERATURE,
};
std::string grammar; // optional BNF-like grammar to constrain sampling
std::string grammar; // optional BNF-like grammar to constrain sampling
bool grammar_lazy = false;
std::vector<common_grammar_trigger> grammar_trigger_words; // optional trigger words to trigger lazy grammar
std::vector<llama_token> grammar_trigger_tokens; // optional trigger tokens to trigger lazy grammar and print trigger special tokens.
std::set<llama_token> preserved_tokens;
std::vector<llama_logit_bias> logit_bias; // logit biases to apply
@ -603,10 +613,18 @@ std::string common_detokenize(
// Chat template utils
//
struct common_tool_call {
std::string name;
std::string arguments;
std::string id;
};
// same with llama_chat_message, but uses std::string
struct common_chat_msg {
std::string role;
std::string content;
std::vector<common_tool_call> tool_calls;
std::string tool_plan = "";
};
// Check if the template supplied via "--chat-template" is supported or not. Returns true if it's valid