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

llama : remove deprecated API (#5770)

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-02-28 18:43:38 +02:00 • committed by GitHub
parent 78aacf3634
commit 08c5ee87e4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 1 additions and 132 deletions
Download patch file Download diff file Expand all files Collapse all files

88
llama.cpp
View file

@ -7894,9 +7894,9 @@ static int llama_decode_internal(
const auto n_batch = cparams.n_batch;
GGML_ASSERT(n_tokens <= n_batch);
GGML_ASSERT((!batch.token && batch.embd) || (batch.token && !batch.embd)); // NOLINT
int n_threads = n_tokens == 1 ? cparams.n_threads : cparams.n_threads_batch;
GGML_ASSERT((!batch.token && batch.embd) || (batch.token && !batch.embd)); // NOLINT
const int64_t t_start_us = ggml_time_us();
@ -10062,10 +10062,6 @@ void llama_sample_temp(struct llama_context * ctx, llama_token_data_array * cand
}
}
void llama_sample_temperature(struct llama_context * ctx, llama_token_data_array * candidates_p, float temp) {
llama_sample_temp(ctx, candidates_p, temp);
}
void llama_sample_repetition_penalties(
struct llama_context * ctx,
llama_token_data_array * candidates,
@ -10192,38 +10188,6 @@ void llama_sample_apply_guidance(
ctx->t_sample_us += ggml_time_us() - t_start_sample_us;
}
void llama_sample_classifier_free_guidance(
struct llama_context * ctx,
llama_token_data_array * candidates,
struct llama_context * guidance_ctx,
float scale) {
GGML_ASSERT(ctx);
int64_t t_start_sample_us;
t_start_sample_us = ggml_time_us();
const size_t n_vocab = llama_n_vocab(llama_get_model(ctx));
GGML_ASSERT(n_vocab == candidates->size);
GGML_ASSERT(!candidates->sorted);
std::vector<float> logits_base(n_vocab);
for (size_t i = 0; i < n_vocab; ++i) {
logits_base[i] = candidates->data[i].logit;
}
float * logits_guidance = llama_get_logits(guidance_ctx);
ctx->t_sample_us += ggml_time_us() - t_start_sample_us;
llama_sample_apply_guidance(ctx, logits_base.data(), logits_guidance, scale);
t_start_sample_us = ggml_time_us();
for (size_t i = 0; i < n_vocab; ++i) {
candidates->data[i].logit = logits_base[i];
}
ctx->t_sample_us += ggml_time_us() - t_start_sample_us;
}
llama_token llama_sample_token_mirostat(struct llama_context * ctx, llama_token_data_array * candidates, float tau, float eta, int32_t m, float * mu) {
GGML_ASSERT(ctx);
@ -11724,15 +11688,6 @@ bool llama_supports_gpu_offload(void) {
#endif
}
// deprecated:
bool llama_mmap_supported(void) {
return llama_supports_mmap();
}
bool llama_mlock_supported(void) {
return llama_supports_mlock();
}
void llama_backend_init(void) {
ggml_time_init();
@ -12244,15 +12199,6 @@ uint32_t llama_model_quantize(
}
}
int32_t llama_apply_lora_from_file(struct llama_context * ctx, const char * path_lora, float scale, const char * path_base_model, int32_t n_threads) {
try {
return llama_apply_lora_from_file_internal(ctx->model, path_lora, scale, path_base_model, n_threads);
} catch (const std::exception & err) {
LLAMA_LOG_ERROR("%s: failed to apply lora adapter: %s\n", __func__, err.what());
return 1;
}
}
int32_t llama_model_apply_lora_from_file(const struct llama_model * model, const char * path_lora, float scale, const char * path_base_model, int32_t n_threads) {
try {
return llama_apply_lora_from_file_internal(*model, path_lora, scale, path_base_model, n_threads);
@ -12802,38 +12748,6 @@ bool llama_save_session_file(struct llama_context * ctx, const char * path_sessi
return true;
}
int llama_eval(
struct llama_context * ctx,
llama_token * tokens,
int32_t n_tokens,
int32_t n_past) {
llama_kv_cache_seq_rm(ctx->kv_self, -1, n_past, -1);
const int ret = llama_decode_internal(*ctx, llama_batch_get_one(tokens, n_tokens, n_past, 0));
if (ret < 0) {
LLAMA_LOG_ERROR("%s: failed to decode, ret = %d\n", __func__, ret);
}
return ret;
}
int llama_eval_embd(
struct llama_context * ctx,
float * embd,
int32_t n_tokens,
int32_t n_past) {
llama_kv_cache_seq_rm(ctx->kv_self, -1, n_past, -1);
llama_batch batch = { n_tokens, nullptr, embd, nullptr, nullptr, nullptr, nullptr, n_past, 1, 0, };
const int ret = llama_decode_internal(*ctx, batch);
if (ret < 0) {
LLAMA_LOG_ERROR("%s: failed to decode, ret = %d\n", __func__, ret);
}
return ret;
}
void llama_set_n_threads(struct llama_context * ctx, uint32_t n_threads, uint32_t n_threads_batch) {
ctx->cparams.n_threads = n_threads;
ctx->cparams.n_threads_batch = n_threads_batch;