ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-29 19:01:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge mainline llama.cpp (#3)

Browse Source 
* Merging mainline - WIP

* Merging mainline - WIP

AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.

* Merging mainline - fix Metal

* Remove check

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-07-27 07:55:01 +02:00
committed by GitHub
parent afd9fd274e
commit 0ceeb11721
612 changed files with 50817 additions and 165936 deletions
Download Patch File Download Diff File Expand all files Collapse all files

81
common/common.h
View File

@@ -52,6 +52,12 @@ int32_t cpu_get_num_math();
// CLI argument parsing
//
// dimensionality reduction methods, used by cvector-generator
enum dimre_method {
DIMRE_METHOD_PCA,
DIMRE_METHOD_MEAN,
};
struct gpt_params {
uint32_t seed = LLAMA_DEFAULT_SEED; // RNG seed
@@ -93,6 +99,7 @@ struct gpt_params {
enum llama_split_mode split_mode = LLAMA_SPLIT_MODE_LAYER; // how to split the model across GPUs
enum llama_rope_scaling_type rope_scaling_type = LLAMA_ROPE_SCALING_TYPE_UNSPECIFIED;
enum llama_pooling_type pooling_type = LLAMA_POOLING_TYPE_UNSPECIFIED; // pooling type for embeddings
enum llama_attention_type attention_type = LLAMA_ATTENTION_TYPE_UNSPECIFIED; // attention type for embeddings
// // sampling parameters
struct llama_sampling_params sparams;
@@ -101,6 +108,7 @@ struct gpt_params {
std::string model_draft = ""; // draft model for speculative decoding
std::string model_alias = "unknown"; // model alias
std::string model_url = ""; // model url to download
std::string hf_token = ""; // HF token
std::string hf_repo = ""; // HF repo
std::string hf_file = ""; // HF file
std::string prompt = "";
@@ -120,7 +128,6 @@ struct gpt_params {
// TODO: avoid tuple, use struct
std::vector<std::tuple<std::string, float>> lora_adapter; // lora adapter path with user defined scale
std::string lora_base = ""; // base model path for the lora adapter
std::vector<llama_control_vector_load_info> control_vectors; // control vector with user defined scale
@@ -152,7 +159,6 @@ struct gpt_params {
bool prompt_cache_all = false; // save user input and generations to prompt cache
bool prompt_cache_ro = false; // open the prompt cache read-only and do not update it
bool embedding = false; // get only sentence embedding
bool escape = true; // escape "\n", "\r", "\t", "\'", "\"", and "\\"
bool multiline_input = false; // reverse the usage of `\`
bool simple_io = false; // improves compatibility with subprocesses and limited consoles
@@ -179,6 +185,12 @@ struct gpt_params {
std::string mmproj = ""; // path to multimodal projector
std::vector<std::string> image; // path to image file(s)
// embedding
bool embedding = false; // get only sentence embedding
int32_t embd_normalize = 2; // normalisation for embendings (-1=none, 0=max absolute int16, 1=taxicab, 2=euclidean, >2=p-norm)
std::string embd_out = ""; // empty = default, "array" = [[],[]...], "json" = openai style, "json+" = same "json" + cosine similarity matrix
std::string embd_sep = "\n"; // separator of embendings
// server params
int32_t port = 8080; // server listens on this network port
int32_t timeout_read = 600; // http read timeout in seconds
@@ -189,6 +201,7 @@ struct gpt_params {
std::string public_path = "";
std::string chat_template = "";
std::string system_prompt = "";
bool enable_chat_template = true;
std::vector<std::string> api_keys;
@@ -234,15 +247,19 @@ struct gpt_params {
bool compute_ppl = true; // whether to compute perplexity
// cvector-generator params
int n_completions = 64;
int n_pca_batch = 20;
int n_pca_batch = 100;
int n_pca_iterations = 1000;
std::string cvector_outfile = "control_vector.gguf";
std::string cvector_completions_file = "examples/cvector-generator/completions.txt";
std::string cvector_positive_file = "examples/cvector-generator/positive.txt";
std::string cvector_negative_file = "examples/cvector-generator/negative.txt";
dimre_method cvector_dimre_method = DIMRE_METHOD_PCA;
std::string cvector_outfile = "control_vector.gguf";
std::string cvector_positive_file = "examples/cvector-generator/positive.txt";
std::string cvector_negative_file = "examples/cvector-generator/negative.txt";
bool spm_infill = false; // suffix/prefix/middle pattern for infill
std::string lora_outfile = "ggml-lora-merged-f16.gguf";
};
void gpt_params_handle_hf_token(gpt_params & params);
void gpt_params_handle_model_default(gpt_params & params);
bool gpt_params_parse_ex (int argc, char ** argv, gpt_params & params);
@@ -298,8 +315,8 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
struct llama_model_params llama_model_params_from_gpt_params (const gpt_params & params);
struct llama_context_params llama_context_params_from_gpt_params(const gpt_params & params);
struct llama_model * llama_load_model_from_url(const char * model_url, const char * path_model, const struct llama_model_params & params);
struct llama_model * llama_load_model_from_hf(const char * repo, const char * file, const char * path_model, const struct llama_model_params & params);
struct llama_model * llama_load_model_from_url(const char * model_url, const char * path_model, const char * hf_token, const struct llama_model_params & params);
struct llama_model * llama_load_model_from_hf(const char * repo, const char * file, const char * path_model, const char * hf_token, const struct llama_model_params & params);
// Batch utils
@@ -337,21 +354,13 @@ std::string llama_token_to_piece(
llama_token token,
bool special = true);
// TODO: these should be moved in llama.h C-style API under single `llama_detokenize` function
// that takes into account the tokenizer type and decides how to handle the leading space
//
// detokenizes a vector of tokens into a string
// should work similar to Python's `tokenizer.decode`
// removes the leading space from the first non-BOS token
std::string llama_detokenize_spm(
// optionally renders special/control tokens
std::string llama_detokenize(
llama_context * ctx,
const std::vector<llama_token> & tokens);
// detokenizes a vector of tokens into a string
// should work similar to Python's `tokenizer.decode`
std::string llama_detokenize_bpe(
llama_context * ctx,
const std::vector<llama_token> & tokens);
const std::vector<llama_token> & tokens,
bool special = true);
// Uses the value from the model metadata if possible, otherwise
// defaults to true when model type is SPM, otherwise false.
@@ -361,9 +370,34 @@ bool llama_should_add_bos_token(const llama_model * model);
// Chat template utils
//
// same with llama_chat_message, but uses std::string
struct llama_chat_msg {
std::string role;
std::string content;
};
// Check if the template supplied via "--chat-template" is supported or not. Returns true if it's valid
bool llama_chat_verify_template(const std::string & tmpl);
// CPP wrapper for llama_chat_apply_template
// If the built-in template is not supported, we default to chatml
// If the custom "tmpl" is not supported, we throw an error
std::string llama_chat_apply_template(const struct llama_model * model,
const std::string & tmpl,
const std::vector<llama_chat_msg> & chat,
bool add_ass);
// Format single message, while taking into account the position of that message in chat history
std::string llama_chat_format_single(const struct llama_model * model,
const std::string & tmpl,
const std::vector<llama_chat_msg> & past_msg,
const llama_chat_msg & new_msg,
bool add_ass);
// Returns an example of formatted chat
std::string llama_chat_format_example(const struct llama_model * model,
const std::string & tmpl);
//
// KV cache utils
//
@@ -378,7 +412,7 @@ void llama_kv_cache_dump_view_seqs(const llama_kv_cache_view & view, int row_siz
// Embedding utils
//
void llama_embd_normalize(const float * inp, float * out, int n);
void llama_embd_normalize(const float * inp, float * out, int n, int embd_norm = 2);
float llama_embd_similarity_cos(const float * embd1, const float * embd2, int n);
@@ -422,4 +456,3 @@ void yaml_dump_string_multiline(FILE * stream, const char * prop_name, const cha
void yaml_dump_non_result_info(
FILE * stream, const gpt_params & params, const llama_context * lctx,
const std::string & timestamp, const std::vector<int> & prompt_tokens, const char * model_desc);