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

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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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);
}