CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-29 08:41:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : add llama_vocab, functions -> methods, naming (#11110)

Browse Source 
* llama : functions -> methods (#11110)

* llama : add struct llama_vocab to the API (#11156)

ggml-ci

* hparams : move vocab params to llama_vocab (#11159)

ggml-ci

* vocab : more pimpl (#11165)

ggml-ci

* vocab : minor tokenization optimizations (#11160)

ggml-ci

Co-authored-by: Diego Devesa <slarengh@gmail.com>

* lora : update API names (#11167)

ggml-ci

* llama : update API names to use correct prefix (#11174)

* llama : update API names to use correct prefix

ggml-ci

* cont

ggml-ci

* cont

ggml-ci

* minor [no ci]

* vocab : llama_vocab_add_[be]os -> llama_vocab_get_add_[be]os (#11174)

ggml-ci

* vocab : llama_vocab_n_vocab -> llama_vocab_n_tokens (#11174)

ggml-ci

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov
2025-01-12 11:32:42 +02:00
committed by GitHub
parent c05e8c9934
commit afa8a9ec9b
68 changed files with 5855 additions and 5400 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
examples/server/server.cpp
View File

@@ -98,7 +98,7 @@ struct slot_params {
int64_t t_max_prompt_ms = -1; // TODO: implement
int64_t t_max_predict_ms = -1; // if positive, limit the generation phase to this time limit
std::vector<common_lora_adapter_info> lora;
std::vector<common_adapter_lora_info> lora;
std::vector<std::string> antiprompt;
std::vector<std::string> response_fields;
@@ -198,15 +198,17 @@ struct server_task {
bool metrics_reset_bucket = false;
// used by SERVER_TASK_TYPE_SET_LORA
std::vector<common_lora_adapter_info> set_lora;
std::vector<common_adapter_lora_info> set_lora;
server_task(server_task_type type) : type(type) {}
static slot_params params_from_json_cmpl(
const llama_model * model,
const llama_context * ctx,
const common_params & params_base,
const json & data) {
const llama_model * model = llama_get_model(ctx);
const llama_vocab * vocab = llama_model_get_vocab(model);
slot_params params;
// Sampling parameter defaults are loaded from the global server context (but individual requests can still override them)
@@ -329,7 +331,7 @@ struct server_task {
const auto & logit_bias = data.find("logit_bias");
if (logit_bias != data.end() && logit_bias->is_array()) {
const int n_vocab = llama_n_vocab(model);
const int n_vocab = llama_vocab_n_tokens(vocab);
for (const auto & el : *logit_bias) {
// TODO: we may want to throw errors here, in case "el" is incorrect
if (el.is_array() && el.size() == 2) {
@@ -348,7 +350,7 @@ struct server_task {
params.sampling.logit_bias.push_back({tok, bias});
}
} else if (el[0].is_string()) {
auto toks = common_tokenize(model, el[0].get<std::string>(), false);
auto toks = common_tokenize(vocab, el[0].get<std::string>(), false);
for (auto tok : toks) {
params.sampling.logit_bias.push_back({tok, bias});
}
@@ -1131,7 +1133,7 @@ struct server_slot {
common_speculative * spec = nullptr;
std::vector<common_lora_adapter_info> lora;
std::vector<common_adapter_lora_info> lora;
// the index relative to completion multi-task request
size_t index = 0;
@@ -1633,6 +1635,8 @@ struct server_context {
llama_model * model = nullptr;
llama_context * ctx = nullptr;
const llama_vocab * vocab = nullptr;
llama_model * model_dft = nullptr;
llama_context_params cparams_dft;
@@ -1690,10 +1694,12 @@ struct server_context {
return false;
}
vocab = llama_model_get_vocab(model);
n_ctx = llama_n_ctx(ctx);
add_bos_token = llama_add_bos_token(model);
has_eos_token = llama_token_eos(model) != LLAMA_TOKEN_NULL;
add_bos_token = llama_vocab_get_add_bos(vocab);
has_eos_token = llama_vocab_eos(vocab) != LLAMA_TOKEN_NULL;
if (!params_base.speculative.model.empty()) {
SRV_INF("loading draft model '%s'\n", params_base.speculative.model.c_str());
@@ -1736,7 +1742,8 @@ struct server_context {
bool validate_builtin_chat_template() const {
llama_chat_message chat[] = {{"user", "test"}};
int32_t chat_res = llama_chat_apply_template(model, nullptr, chat, 1, true, nullptr, 0);
const char * tmpl = llama_model_chat_template(model);
const int32_t chat_res = llama_chat_apply_template(tmpl, chat, 1, true, nullptr, 0);
return chat_res > 0;
}
@@ -1756,7 +1763,7 @@ struct server_context {
if (model_dft) {
slot.batch_spec = llama_batch_init(params_base.speculative.n_max + 1, 0, 1);
slot.ctx_dft = llama_new_context_with_model(model_dft, cparams_dft);
slot.ctx_dft = llama_init_from_model(model_dft, cparams_dft);
if (slot.ctx_dft == nullptr) {
SRV_ERR("%s", "failed to create draft context\n");
return;
@@ -1891,7 +1898,7 @@ struct server_context {
}
if (slot.params.ignore_eos && has_eos_token) {
slot.params.sampling.logit_bias.push_back({llama_token_eos(model), -INFINITY});
slot.params.sampling.logit_bias.push_back({llama_vocab_eos(vocab), -INFINITY});
}
{
@@ -2047,14 +2054,14 @@ struct server_context {
slot.n_decoded, slot.n_prompt_tokens, slot.n_past, slot.n_ctx);
}
if (llama_token_is_eog(model, result.tok)) {
if (llama_vocab_is_eog(vocab, result.tok)) {
slot.stop = STOP_TYPE_EOS;
slot.has_next_token = false;
SLT_DBG(slot, "%s", "stopped by EOS\n");
}
const auto n_ctx_train = llama_n_ctx_train(model);
const auto n_ctx_train = llama_model_n_ctx_train(model);
if (slot.params.n_predict < 1 && slot.n_predict < 1 && slot.n_prompt_tokens + slot.n_decoded >= n_ctx_train) {
slot.truncated = true;
@@ -2074,7 +2081,7 @@ struct server_context {
void populate_token_probs(const server_slot & slot, completion_token_output & result, bool post_sampling, bool special, int idx) {
size_t n_probs = slot.params.sampling.n_probs;
size_t n_vocab = llama_n_vocab(llama_get_model(ctx));
size_t n_vocab = llama_vocab_n_tokens(vocab);
if (post_sampling) {
const auto * cur_p = common_sampler_get_candidates(slot.smpl);
const size_t max_probs = cur_p->size;
@@ -2225,7 +2232,7 @@ struct server_context {
res->n_tokens = slot.n_prompt_tokens;
res->oaicompat = slot.params.oaicompat;
const int n_embd = llama_n_embd(model);
const int n_embd = llama_model_n_embd(model);
std::vector<float> embd_res(n_embd, 0.0f);
@@ -2927,7 +2934,7 @@ struct server_context {
// make sure we're in the right embedding mode
llama_set_embeddings(ctx, slot_batched->is_non_causal());
// apply lora, only need to do it once per batch
common_lora_adapters_apply(ctx, slot_batched->lora);
common_set_adapter_lora(ctx, slot_batched->lora);
}
// process the created batch of tokens
@@ -3129,12 +3136,12 @@ struct server_context {
json model_meta() const {
return json {
{"vocab_type", llama_vocab_type (model)},
{"n_vocab", llama_n_vocab (model)},
{"n_ctx_train", llama_n_ctx_train (model)},
{"n_embd", llama_n_embd (model)},
{"n_params", llama_model_n_params(model)},
{"size", llama_model_size (model)},
{"vocab_type", llama_vocab_type (vocab)},
{"n_vocab", llama_vocab_n_tokens (vocab)},
{"n_ctx_train", llama_model_n_ctx_train(model)},
{"n_embd", llama_model_n_embd (model)},
{"n_params", llama_model_n_params (model)},
{"size", llama_model_size (model)},
};
}
};
@@ -3639,7 +3646,7 @@ int main(int argc, char ** argv) {
std::vector<server_task> tasks;
try {
std::vector<llama_tokens> tokenized_prompts = tokenize_input_prompts(ctx_server.ctx, data.at("prompt"), true, true);
std::vector<llama_tokens> tokenized_prompts = tokenize_input_prompts(ctx_server.vocab, data.at("prompt"), true, true);
tasks.reserve(tokenized_prompts.size());
for (size_t i = 0; i < tokenized_prompts.size(); i++) {
server_task task = server_task(type);
@@ -3649,7 +3656,6 @@ int main(int argc, char ** argv) {
task.prompt_tokens = std::move(tokenized_prompts[i]);
task.params = server_task::params_from_json_cmpl(
ctx_server.model,
ctx_server.ctx,
ctx_server.params_base,
data);
@@ -3745,13 +3751,13 @@ int main(int argc, char ** argv) {
const auto handle_infill = [&ctx_server, &res_error, &handle_completions_impl](const httplib::Request & req, httplib::Response & res) {
// check model compatibility
std::string err;
if (llama_token_fim_pre(ctx_server.model) == LLAMA_TOKEN_NULL) {
if (llama_vocab_fim_pre(ctx_server.vocab) == LLAMA_TOKEN_NULL) {
err += "prefix token is missing. ";
}
if (llama_token_fim_suf(ctx_server.model) == LLAMA_TOKEN_NULL) {
if (llama_vocab_fim_suf(ctx_server.vocab) == LLAMA_TOKEN_NULL) {
err += "suffix token is missing. ";
}
if (llama_token_fim_mid(ctx_server.model) == LLAMA_TOKEN_NULL) {
if (llama_vocab_fim_mid(ctx_server.vocab) == LLAMA_TOKEN_NULL) {
err += "middle token is missing. ";
}
if (!err.empty()) {
@@ -3797,10 +3803,10 @@ int main(int argc, char ** argv) {
data["input_extra"] = input_extra; // default to empty array if it's not exist
std::string prompt = json_value(data, "prompt", std::string());
std::vector<llama_tokens> tokenized_prompts = tokenize_input_prompts(ctx_server.ctx, prompt, false, true);
std::vector<llama_tokens> tokenized_prompts = tokenize_input_prompts(ctx_server.vocab, prompt, false, true);
SRV_DBG("creating infill tasks, n_prompts = %d\n", (int) tokenized_prompts.size());
data["prompt"] = format_infill(
ctx_server.ctx,
ctx_server.vocab,
data.at("input_prefix"),
data.at("input_suffix"),
data.at("input_extra"),
@@ -3857,7 +3863,7 @@ int main(int argc, char ** argv) {
const bool add_special = json_value(body, "add_special", false);
const bool with_pieces = json_value(body, "with_pieces", false);
llama_tokens tokens = tokenize_mixed(ctx_server.ctx, body.at("content"), add_special, true);
llama_tokens tokens = tokenize_mixed(ctx_server.vocab, body.at("content"), add_special, true);
if (with_pieces) {
for (const auto& token : tokens) {
@@ -3933,7 +3939,7 @@ int main(int argc, char ** argv) {
}
}
std::vector<llama_tokens> tokenized_prompts = tokenize_input_prompts(ctx_server.ctx, prompt, true, true);
std::vector<llama_tokens> tokenized_prompts = tokenize_input_prompts(ctx_server.vocab, prompt, true, true);
for (const auto & tokens : tokenized_prompts) {
// this check is necessary for models that do not add BOS token to the input
if (tokens.empty()) {
@@ -4033,20 +4039,20 @@ int main(int argc, char ** argv) {
return;
}
llama_tokens tokenized_query = tokenize_input_prompts(ctx_server.ctx, query, /* add_special */ false, true)[0];
llama_tokens tokenized_query = tokenize_input_prompts(ctx_server.vocab, query, /* add_special */ false, true)[0];
// create and queue the task
json responses = json::array();
bool error = false;
{
std::vector<server_task> tasks;
std::vector<llama_tokens> tokenized_docs = tokenize_input_prompts(ctx_server.ctx, documents, /* add_special */ false, true);
std::vector<llama_tokens> tokenized_docs = tokenize_input_prompts(ctx_server.vocab, documents, /* add_special */ false, true);
tasks.reserve(tokenized_docs.size());
for (size_t i = 0; i < tokenized_docs.size(); i++) {
server_task task = server_task(SERVER_TASK_TYPE_RERANK);
task.id = ctx_server.queue_tasks.get_new_id();
task.index = i;
task.prompt_tokens = format_rerank(ctx_server.model, tokenized_query, tokenized_docs[i]);
task.prompt_tokens = format_rerank(ctx_server.vocab, tokenized_query, tokenized_docs[i]);
tasks.push_back(task);
}

83
examples/server/utils.hpp
View File

@@ -118,7 +118,7 @@ static json json_get_nested_values(const std::vector<std::string> & paths, const
* - only string, example: "string"
* - mixed string and tokens, example: [12, 34, "string", 56, 78]
*/
static llama_tokens tokenize_mixed(const llama_context * ctx, const json & json_prompt, bool add_special, bool parse_special) {
static llama_tokens tokenize_mixed(const llama_vocab * vocab, const json & json_prompt, bool add_special, bool parse_special) {
// If `add_bos` is true, we only add BOS, when json_prompt is a string,
// or the first element of the json_prompt array is a string.
llama_tokens prompt_tokens;
@@ -131,10 +131,10 @@ static llama_tokens tokenize_mixed(const llama_context * ctx, const json & json_
llama_tokens p;
if (first) {
p = common_tokenize(ctx, s, add_special, parse_special);
p = common_tokenize(vocab, s, add_special, parse_special);
first = false;
} else {
p = common_tokenize(ctx, s, false, parse_special);
p = common_tokenize(vocab, s, false, parse_special);
}
prompt_tokens.insert(prompt_tokens.end(), p.begin(), p.end());
@@ -148,7 +148,7 @@ static llama_tokens tokenize_mixed(const llama_context * ctx, const json & json_
}
} else {
auto s = json_prompt.template get<std::string>();
prompt_tokens = common_tokenize(ctx, s, add_special, parse_special);
prompt_tokens = common_tokenize(vocab, s, add_special, parse_special);
}
return prompt_tokens;
@@ -166,11 +166,11 @@ static llama_tokens tokenize_mixed(const llama_context * ctx, const json & json_
* - "prompt": [[12, 34, 56], [78, 90, 12]]
* - "prompt": [[12, 34, "string", 56, 78], [12, 34, 56]]
*/
static std::vector<llama_tokens> tokenize_input_prompts(llama_context * ctx, const json & json_prompt, bool add_special, bool parse_special) {
static std::vector<llama_tokens> tokenize_input_prompts(const llama_vocab * vocab, const json & json_prompt, bool add_special, bool parse_special) {
std::vector<llama_tokens> result;
if (json_prompt.is_string() || json_is_array_of_mixed_numbers_strings(json_prompt)) {
// string or mixed
result.push_back(tokenize_mixed(ctx, json_prompt, add_special, parse_special));
result.push_back(tokenize_mixed(vocab, json_prompt, add_special, parse_special));
} else if (json_is_array_of_numbers(json_prompt)) {
// array of tokens
result.push_back(json_prompt.get<llama_tokens>());
@@ -179,7 +179,7 @@ static std::vector<llama_tokens> tokenize_input_prompts(llama_context * ctx, con
result.reserve(json_prompt.size());
for (const auto & p : json_prompt) {
if (p.is_string() || json_is_array_of_mixed_numbers_strings(p)) {
result.push_back(tokenize_mixed(ctx, p, add_special, parse_special));
result.push_back(tokenize_mixed(vocab, p, add_special, parse_special));
} else if (json_is_array_of_numbers(p)) {
// array of tokens
result.push_back(p.get<llama_tokens>());
@@ -231,21 +231,23 @@ static size_t validate_utf8(const std::string& text) {
//
// format rerank task: [BOS]query[EOS][SEP]doc[EOS]
static llama_tokens format_rerank(const struct llama_model * model, const llama_tokens & query, const llama_tokens & doc) {
static llama_tokens format_rerank(const struct llama_vocab * vocab, const llama_tokens & query, const llama_tokens & doc) {
llama_tokens result;
result.reserve(doc.size() + query.size() + 4);
result.push_back(llama_token_bos(model));
result.push_back(llama_vocab_bos(vocab));
result.insert(result.end(), query.begin(), query.end());
result.push_back(llama_token_eos(model));
result.push_back(llama_token_sep(model));
result.push_back(llama_vocab_eos(vocab));
result.push_back(llama_vocab_sep(vocab));
result.insert(result.end(), doc.begin(), doc.end());
result.push_back(llama_token_eos(model));
result.push_back(llama_vocab_eos(vocab));
return result;
}
// format infill task
static llama_tokens format_infill(
const llama_context * ctx,
const llama_vocab * vocab,
const json & input_prefix,
const json & input_suffix,
const json & input_extra,
@@ -272,15 +274,14 @@ static llama_tokens format_infill(
llama_tokens extra_tokens;
extra_tokens.reserve(n_ctx);
auto model = llama_get_model(ctx);
auto tokens_prefix = tokenize_mixed(ctx, input_prefix, false, false);
auto tokens_suffix = tokenize_mixed(ctx, input_suffix, false, false);
auto tokens_prefix = tokenize_mixed(vocab, input_prefix, false, false);
auto tokens_suffix = tokenize_mixed(vocab, input_suffix, false, false);
if (llama_token_fim_rep(model) != LLAMA_TOKEN_NULL) {
if (llama_vocab_fim_rep(vocab) != LLAMA_TOKEN_NULL) {
// TODO: make project name an input
static const auto k_fim_repo = common_tokenize(ctx, "myproject\n", false, false);
static const auto k_fim_repo = common_tokenize(vocab, "myproject\n", false, false);
extra_tokens.push_back(llama_token_fim_rep(model));
extra_tokens.push_back(llama_vocab_fim_rep(vocab));
extra_tokens.insert(extra_tokens.end(), k_fim_repo.begin(), k_fim_repo.end());
}
for (const auto & chunk : input_extra) {
@@ -288,28 +289,28 @@ static llama_tokens format_infill(
const std::string text = json_value(chunk, "text", std::string());
const std::string filename = json_value(chunk, "filename", std::string("tmp"));
if (llama_token_fim_sep(model) != LLAMA_TOKEN_NULL) {
const auto k_fim_file = common_tokenize(ctx, filename + "\n", false, false);
if (llama_vocab_fim_sep(vocab) != LLAMA_TOKEN_NULL) {
const auto k_fim_file = common_tokenize(vocab, filename + "\n", false, false);
extra_tokens.insert(extra_tokens.end(), llama_token_fim_sep(model));
extra_tokens.insert(extra_tokens.end(), llama_vocab_fim_sep(vocab));
extra_tokens.insert(extra_tokens.end(), k_fim_file.begin(), k_fim_file.end());
} else {
// chunk separator in binary form to avoid confusing the AI
static const char k_chunk_prefix_str[] = {0x0a, 0x0a, 0x2d, 0x2d, 0x2d, 0x20, 0x73, 0x6e, 0x69, 0x70, 0x70, 0x65, 0x74, 0x20, 0x2d, 0x2d, 0x2d, 0x0a, 0x0a, 0x00};
static const auto k_chunk_prefix_tokens = common_tokenize(ctx, k_chunk_prefix_str, false, false);
static const auto k_chunk_prefix_tokens = common_tokenize(vocab, k_chunk_prefix_str, false, false);
extra_tokens.insert(extra_tokens.end(), k_chunk_prefix_tokens.begin(), k_chunk_prefix_tokens.end());
}
const auto chunk_tokens = common_tokenize(ctx, text, false, false);
const auto chunk_tokens = common_tokenize(vocab, text, false, false);
extra_tokens.insert(extra_tokens.end(), chunk_tokens.begin(), chunk_tokens.end());
}
if (llama_token_fim_sep(model) != LLAMA_TOKEN_NULL) {
if (llama_vocab_fim_sep(vocab) != LLAMA_TOKEN_NULL) {
// TODO: current filename
static const auto k_fim_file = common_tokenize(ctx, "filename\n", false, false);
static const auto k_fim_file = common_tokenize(vocab, "filename\n", false, false);
extra_tokens.insert(extra_tokens.end(), llama_token_fim_sep(model));
extra_tokens.insert(extra_tokens.end(), llama_vocab_fim_sep(vocab));
extra_tokens.insert(extra_tokens.end(), k_fim_file.begin(), k_fim_file.end());
}
@@ -325,15 +326,15 @@ static llama_tokens format_infill(
tokens_prefix.erase(tokens_prefix.begin(), tokens_prefix.begin() + tokens_prefix.size() - n_prefix_take);
tokens_suffix.resize(n_suffix_take);
tokens_prefix.insert(tokens_prefix.begin(), llama_token_fim_pre(model));
tokens_prefix.insert(tokens_prefix.begin(), llama_vocab_fim_pre(vocab));
tokens_prefix.insert(tokens_prefix.end(), tokens_prompt.begin(), tokens_prompt.end());
tokens_suffix.insert(tokens_suffix.begin(), llama_token_fim_suf(model));
tokens_suffix.insert(tokens_suffix.begin(), llama_vocab_fim_suf(vocab));
auto embd_inp = spm_infill ? tokens_suffix : tokens_prefix;
auto embd_end = spm_infill ? tokens_prefix : tokens_suffix;
if (llama_add_bos_token(model)) {
embd_inp.insert(embd_inp.begin(), llama_token_bos(model));
if (llama_vocab_get_add_bos(vocab)) {
embd_inp.insert(embd_inp.begin(), llama_vocab_bos(vocab));
}
SRV_DBG("extra: n_ctx = %d, n_extra_take = %d, n_extra = %d\n", n_ctx, n_extra_take, (int) extra_tokens.size());
@@ -342,7 +343,7 @@ static llama_tokens format_infill(
embd_inp.insert(embd_inp.begin(), extra_tokens.end() - n_extra_take, extra_tokens.end());
embd_inp.insert(embd_inp.end(), embd_end.begin(), embd_end.end());
embd_inp.push_back(llama_token_fim_mid(model));
embd_inp.push_back(llama_vocab_fim_mid(vocab));
return embd_inp;
}
@@ -764,14 +765,18 @@ static json format_logit_bias(const std::vector<llama_logit_bias> & logit_bias)
return data;
}
static std::string safe_json_to_str(json data) {
static std::string safe_json_to_str(const json & data) {
return data.dump(-1, ' ', false, json::error_handler_t::replace);
}
static std::vector<llama_token_data> get_token_probabilities(llama_context * ctx, int idx) {
std::vector<llama_token_data> cur;
const auto * logits = llama_get_logits_ith(ctx, idx);
const int n_vocab = llama_n_vocab(llama_get_model(ctx));
const llama_model * model = llama_get_model(ctx);
const llama_vocab * vocab = llama_model_get_vocab(model);
const int n_vocab = llama_vocab_n_tokens(vocab);
cur.resize(n_vocab);
for (llama_token token_id = 0; token_id < n_vocab; token_id++) {
@@ -799,8 +804,8 @@ static std::vector<llama_token_data> get_token_probabilities(llama_context * ctx
}
static bool are_lora_equal(
const std::vector<common_lora_adapter_info> & l1,
const std::vector<common_lora_adapter_info> & l2) {
const std::vector<common_adapter_lora_info> & l1,
const std::vector<common_adapter_lora_info> & l2) {
if (l1.size() != l2.size()) {
return false;
}
@@ -814,10 +819,10 @@ static bool are_lora_equal(
}
// parse lora config from JSON request, returned a copy of lora_base with updated scale
static std::vector<common_lora_adapter_info> parse_lora_request(
const std::vector<common_lora_adapter_info> & lora_base,
static std::vector<common_adapter_lora_info> parse_lora_request(
const std::vector<common_adapter_lora_info> & lora_base,
const json & data) {
std::vector<common_lora_adapter_info> lora(lora_base);
std::vector<common_adapter_lora_info> lora(lora_base);
int max_idx = lora.size();
// clear existing value