vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	Makefile
#	README.md
This commit is contained in:
Concedo 2023-03-26 14:52:08 +08:00
commit 57474944d6
34 changed files with 970 additions and 1116 deletions
Download patch file Download diff file Expand all files Collapse all files

93
llama.cpp
View file

@ -168,9 +168,11 @@ struct llama_context {
int64_t t_sample_us = 0;
int64_t t_eval_us = 0;
int64_t t_p_eval_us = 0;
int32_t n_sample = 0; // number of tokens sampled
int32_t n_eval = 0; // number of eval calls
int32_t n_p_eval = 0; // number of tokens in eval calls for the prompt (with batch size > 1)
llama_model model;
llama_vocab vocab;
@ -239,7 +241,7 @@ static bool kv_cache_init(
const int n_mem = n_layer*n_ctx;
const int n_elements = n_embd*n_mem;
cache.buf.resize(2*n_elements*ggml_type_size(wtype) + 2u*MB);
cache.buf.resize(2u*n_elements*ggml_type_size(wtype) + 2u*MB);
struct ggml_init_params params;
params.mem_size = cache.buf.size();
@ -267,14 +269,16 @@ static void kv_cache_free(struct llama_kv_cache & cache) {
struct llama_context_params llama_context_default_params() {
struct llama_context_params result = {
/*.n_ctx =*/ 512,
/*.n_parts =*/ -1,
/*.seed =*/ 0,
/*.f16_kv =*/ false,
/*.logits_all =*/ false,
/*.vocab_only =*/ false,
/*.use_mlock =*/ false,
/*.embedding =*/ false,
/*.n_ctx =*/ 512,
/*.n_parts =*/ -1,
/*.seed =*/ 0,
/*.f16_kv =*/ false,
/*.logits_all =*/ false,
/*.vocab_only =*/ false,
/*.use_mlock =*/ false,
/*.embedding =*/ false,
/*.progress_callback =*/ nullptr,
/*.progress_callback_user_data =*/ nullptr,
};
return result;
@ -290,7 +294,9 @@ static bool llama_model_load(
int n_ctx,
int n_parts,
ggml_type memory_type,
bool vocab_only) {
bool vocab_only,
llama_progress_callback progress_callback,
void *progress_callback_user_data) {
fprintf(stderr, "%s: loading model from '%s' - please wait ...\n", __func__, fname.c_str());
const int64_t t_start_us = ggml_time_us();
@ -583,6 +589,10 @@ static bool llama_model_load(
std::vector<uint8_t> tmp;
if (progress_callback) {
progress_callback(0.0, progress_callback_user_data);
}
for (int i = 0; i < n_parts; ++i) {
const int part_id = i;
//const int part_id = n_parts - i - 1;
@ -596,6 +606,10 @@ static bool llama_model_load(
fin = std::ifstream(fname_part, std::ios::binary);
fin.rdbuf()->pubsetbuf(f_buf.data(), f_buf.size());
fin.seekg(0, fin.end);
const size_t file_size = fin.tellg();
fin.seekg(file_offset);
// load weights
@ -771,6 +785,11 @@ static bool llama_model_load(
model.n_loaded++;
// progress
if (progress_callback) {
double current_file_progress = double(size_t(fin.tellg()) - file_offset) / double(file_size - file_offset);
double current_progress = (double(i) + current_file_progress) / double(n_parts);
progress_callback(current_progress, progress_callback_user_data);
}
if (model.n_loaded % 8 == 0) {
fprintf(stderr, ".");
fflush(stderr);
@ -793,6 +812,10 @@ static bool llama_model_load(
lctx.t_load_us = ggml_time_us() - t_start_us;
if (progress_callback) {
progress_callback(1.0, progress_callback_user_data);
}
return true;
}
@ -836,8 +859,11 @@ static bool llama_eval_internal(
};
struct ggml_context * ctx0 = ggml_init(params);
// for big prompts, if BLAS is enabled, it is better to use only one thread
// otherwise, the threads are spin-lock waiting for the BLAS calls and are degrading the performance
ggml_cgraph gf = {};
gf.n_threads = n_threads;
gf.n_threads = N > 255 && ggml_cpu_has_blas() ? 1 : n_threads;
struct ggml_tensor * embd = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, N);
memcpy(embd->data, tokens, N*ggml_element_size(embd));
@ -903,8 +929,7 @@ static bool llama_eval_internal(
struct ggml_tensor * KQ_scaled =
ggml_scale(ctx0,
KQ,
ggml_new_f32(ctx0, 1.0f/sqrt(float(n_embd)/n_head))
);
ggml_new_f32(ctx0, 1.0f/sqrt(float(n_embd)/n_head)));
// KQ_masked = mask_past(KQ_scaled)
struct ggml_tensor * KQ_masked = ggml_diag_mask_inf(ctx0, KQ_scaled, n_past);
@ -920,7 +945,7 @@ static bool llama_eval_internal(
ggml_view_1d(ctx0, kv_self.v, (n_past + N)*n_embd, il*n_ctx*ggml_element_size(kv_self.v)*n_embd),
n_embd/n_head, n_head, n_past + N),
1, 2, 0, 3),
ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, n_past + N, n_embd/n_head, n_head));
ggml_new_tensor_3d(ctx0, kv_self.v->type, n_past + N, n_embd/n_head, n_head));
// KQV = transpose(V) * KQ_soft_max
struct ggml_tensor * KQV = ggml_mul_mat(ctx0, V_trans, KQ_soft_max);
@ -1057,6 +1082,10 @@ static bool llama_eval_internal(
lctx.t_eval_us += ggml_time_us() - t_start_us;
lctx.n_eval++;
}
else if (N > 1) {
lctx.t_p_eval_us += ggml_time_us() - t_start_us;
lctx.n_p_eval += N;
}
return true;
}
@ -1239,10 +1268,10 @@ static llama_vocab::id llama_sample_top_p_top_k(
double repeat_penalty) {
auto & rng = lctx.rng;
const auto & vocab = lctx.vocab;
const auto & logits = lctx.logits;
const int n_logits = lctx.model.hparams.n_vocab;
int n_logits = vocab.id_to_token.size();
const auto & logits = lctx.logits;
const auto * plogits = logits.data() + logits.size() - n_logits;
std::vector<std::pair<double, llama_vocab::id>> logits_id;
logits_id.reserve(n_logits);
@ -1254,13 +1283,13 @@ static llama_vocab::id llama_sample_top_p_top_k(
// credit https://github.com/facebookresearch/llama/compare/main...shawwn:llama:main
if (std::find(last_n_tokens.begin(), last_n_tokens.end(), i) != last_n_tokens.end()) {
// if score < 0 then repetition penalty has to multiplied to reduce the previous token probability
if (logits[i] < 0.0) {
logits_id.push_back(std::make_pair(logits[i]*scale*repeat_penalty, i));
if (plogits[i] < 0.0) {
logits_id.push_back(std::make_pair(plogits[i]*scale*repeat_penalty, i));
} else {
logits_id.push_back(std::make_pair(logits[i]*scale/repeat_penalty, i));
logits_id.push_back(std::make_pair(plogits[i]*scale/repeat_penalty, i));
}
} else {
logits_id.push_back(std::make_pair(logits[i]*scale, i));
logits_id.push_back(std::make_pair(plogits[i]*scale, i));
}
}
}
@ -1624,7 +1653,8 @@ struct llama_context * llama_init_from_file(
ggml_type memory_type = params.f16_kv ? GGML_TYPE_F16 : GGML_TYPE_F32;
if (!llama_model_load(path_model, *ctx, params.n_ctx, params.n_parts, memory_type,
params.vocab_only)) {
params.vocab_only, params.progress_callback,
params.progress_callback_user_data)) {
fprintf(stderr, "%s: failed to load model\n", __func__);
llama_free(ctx);
return nullptr;
@ -1654,6 +1684,8 @@ struct llama_context * llama_init_from_file(
}
const auto & hparams = ctx->model.hparams;
// resized during inference
if (params.logits_all) {
ctx->logits.reserve(hparams.n_ctx*hparams.n_vocab);
} else {
@ -1661,7 +1693,7 @@ struct llama_context * llama_init_from_file(
}
if (params.embedding){
ctx->embedding.reserve(hparams.n_embd);
ctx->embedding.resize(hparams.n_embd);
}
ctx->buf_compute.resize(MEM_REQ_EVAL.at(ctx->model.type));
@ -1738,6 +1770,10 @@ int llama_n_ctx(struct llama_context * ctx) {
return ctx->model.hparams.n_ctx;
}
int llama_n_embd(struct llama_context * ctx) {
return ctx->model.hparams.n_embd;
}
float * llama_get_logits(struct llama_context * ctx) {
return ctx->logits.data();
}
@ -1797,12 +1833,14 @@ void llama_print_timings(struct llama_context * ctx) {
const int32_t n_sample = std::max(1, ctx->n_sample);
const int32_t n_eval = std::max(1, ctx->n_eval);
const int32_t n_p_eval = std::max(1, ctx->n_p_eval);
fprintf(stderr, "\n");
fprintf(stderr, "%s: load time = %8.2f ms\n", __func__, ctx->t_load_us / 1000.0f);
fprintf(stderr, "%s: sample time = %8.2f ms / %5d runs (%8.2f ms per run)\n", __func__, 1e-3f * ctx->t_sample_us, n_sample, 1e-3f * ctx->t_sample_us / n_sample);
fprintf(stderr, "%s: eval time = %8.2f ms / %5d runs (%8.2f ms per run)\n", __func__, 1e-3f * ctx->t_eval_us, n_eval, 1e-3f * ctx->t_eval_us / n_eval);
fprintf(stderr, "%s: total time = %8.2f ms\n", __func__, (t_end_us - ctx->t_start_us)/1000.0f);
fprintf(stderr, "%s: load time = %8.2f ms\n", __func__, ctx->t_load_us / 1000.0f);
fprintf(stderr, "%s: sample time = %8.2f ms / %5d runs (%8.2f ms per run)\n", __func__, 1e-3f * ctx->t_sample_us, n_sample, 1e-3f * ctx->t_sample_us / n_sample);
fprintf(stderr, "%s: prompt eval time = %8.2f ms / %5d tokens (%8.2f ms per token)\n", __func__, 1e-3f * ctx->t_p_eval_us, n_p_eval, 1e-3f * ctx->t_p_eval_us / n_p_eval);
fprintf(stderr, "%s: eval time = %8.2f ms / %5d runs (%8.2f ms per run)\n", __func__, 1e-3f * ctx->t_eval_us, n_eval, 1e-3f * ctx->t_eval_us / n_eval);
fprintf(stderr, "%s: total time = %8.2f ms\n", __func__, (t_end_us - ctx->t_start_us)/1000.0f);
}
void llama_reset_timings(struct llama_context * ctx) {
@ -1810,6 +1848,7 @@ void llama_reset_timings(struct llama_context * ctx) {
ctx->t_sample_us = ctx->n_sample = 0;
ctx->t_eval_us = ctx->n_eval = 0;
ctx->t_p_eval_us = ctx->n_p_eval = 0;
}
const char * llama_print_system_info(void) {