vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-12 09:59:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'master' into concedo

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	.gitignore
#	CMakeLists.txt
#	Makefile
This commit is contained in:
Concedo 2023-03-29 21:08:03 +08:00
commit 49c4c225b5
28 changed files with 1089 additions and 729 deletions
Download patch file Download diff file Expand all files Collapse all files

65
llama.cpp
View file

@ -321,7 +321,7 @@ static bool llama_model_load(
uint32_t magic;
fin.read((char *) &magic, sizeof(magic));
if (magic == LLAMA_FILE_MAGIC_UNVERSIONED) {
fprintf(stderr, "%s: invalid model file '%s' (too old, regenerate your model files!)\n",
fprintf(stderr, "%s: invalid model file '%s' (too old, regenerate your model files or convert them with convert-unversioned-ggml-to-ggml.py!)\n",
__func__, fname.c_str());
legacy_file_format = true;
}
@ -786,8 +786,8 @@ static bool llama_model_load(
// 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);
float current_file_progress = float(size_t(fin.tellg()) - file_offset) / float(file_size - file_offset);
float current_progress = (float(i) + current_file_progress) / float(n_parts);
progress_callback(current_progress, progress_callback_user_data);
}
if (model.n_loaded % 8 == 0) {
@ -929,7 +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/sqrtf(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);
@ -1247,12 +1247,12 @@ static std::vector<llama_vocab::id> llama_tokenize(const llama_vocab & vocab, co
// sampling
//
static void sample_top_k(std::vector<std::pair<double, llama_vocab::id>> & logits_id, int top_k) {
static void sample_top_k(std::vector<std::pair<float, llama_vocab::id>> & logits_id, int top_k) {
// find the top k tokens
std::partial_sort(
logits_id.begin(),
logits_id.begin() + top_k, logits_id.end(),
[](const std::pair<double, llama_vocab::id> & a, const std::pair<double, llama_vocab::id> & b) {
[](const std::pair<float, llama_vocab::id> & a, const std::pair<float, llama_vocab::id> & b) {
return a.first > b.first;
});
@ -1263,9 +1263,9 @@ static llama_vocab::id llama_sample_top_p_top_k(
llama_context & lctx,
const std::vector<llama_vocab::id> & last_n_tokens,
int top_k,
double top_p,
double temp,
double repeat_penalty) {
float top_p,
float temp,
float repeat_penalty) {
auto & rng = lctx.rng;
const int n_logits = lctx.model.hparams.n_vocab;
@ -1273,17 +1273,17 @@ static llama_vocab::id llama_sample_top_p_top_k(
const auto & logits = lctx.logits;
const auto * plogits = logits.data() + logits.size() - n_logits;
std::vector<std::pair<double, llama_vocab::id>> logits_id;
std::vector<std::pair<float, llama_vocab::id>> logits_id;
logits_id.reserve(n_logits);
{
const double scale = 1.0/temp;
const float scale = 1.0f/temp;
for (int i = 0; i < n_logits; ++i) {
// repetition penalty from ctrl paper (https://arxiv.org/abs/1909.05858)
// 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 (plogits[i] < 0.0) {
if (plogits[i] < 0.0f) {
logits_id.push_back(std::make_pair(plogits[i]*scale*repeat_penalty, i));
} else {
logits_id.push_back(std::make_pair(plogits[i]*scale/repeat_penalty, i));
@ -1296,18 +1296,18 @@ static llama_vocab::id llama_sample_top_p_top_k(
sample_top_k(logits_id, top_k);
double maxl = -std::numeric_limits<double>::infinity();
float maxl = -std::numeric_limits<float>::infinity();
for (const auto & kv : logits_id) {
maxl = std::max(maxl, kv.first);
}
// compute probs for the top k tokens
std::vector<double> probs;
std::vector<float> probs;
probs.reserve(logits_id.size());
double sum = 0.0;
for (const auto & kv : logits_id) {
double p = exp(kv.first - maxl);
const float p = expf(kv.first - maxl);
probs.push_back(p);
sum += p;
}
@ -1317,8 +1317,8 @@ static llama_vocab::id llama_sample_top_p_top_k(
p /= sum;
}
if (top_p < 1.0f) {
double cumsum = 0.0f;
if (top_p < 1.0) {
double cumsum = 0.0;
for (int i = 0; i < (int) probs.size(); i++) {
cumsum += probs[i];
if (cumsum >= top_p) {
@ -1352,7 +1352,7 @@ static llama_vocab::id llama_sample_top_p_top_k(
//
// TODO: reuse code from the llama_model_load() somehow
bool llama_model_quantize_internal(const std::string & fname_inp, const std::string & fname_out, int itype, int qk) {
static bool llama_model_quantize_internal(const std::string & fname_inp, const std::string & fname_out, int itype) {
ggml_type type = GGML_TYPE_Q4_1;
switch (itype) {
@ -1575,11 +1575,11 @@ bool llama_model_quantize_internal(const std::string & fname_inp, const std::str
switch (type) {
case GGML_TYPE_Q4_0:
{
cur_size = ggml_quantize_q4_0(data_f32.data(), work.data(), nelements, ne[0], qk, hist_cur.data());
cur_size = ggml_quantize_q4_0(data_f32.data(), work.data(), nelements, ne[0], hist_cur.data());
} break;
case GGML_TYPE_Q4_1:
{
cur_size = ggml_quantize_q4_1(data_f32.data(), work.data(), nelements, ne[0], qk, hist_cur.data());
cur_size = ggml_quantize_q4_1(data_f32.data(), work.data(), nelements, ne[0], hist_cur.data());
} break;
default:
{
@ -1597,7 +1597,7 @@ bool llama_model_quantize_internal(const std::string & fname_inp, const std::str
}
for (int i = 0; i < (int) hist_cur.size(); ++i) {
printf("%5.3f ", hist_cur[i] / (float)nelements);
printf("%5.3f ", hist_cur[i] / float(nelements));
}
printf("\n");
} else {
@ -1620,7 +1620,7 @@ bool llama_model_quantize_internal(const std::string & fname_inp, const std::str
printf("%s: hist: ", __func__);
for (int i = 0; i < (int) hist_all.size(); ++i) {
printf("%5.3f ", hist_all[i] / (float)sum_all);
printf("%5.3f ", hist_all[i] / float(sum_all));
}
printf("\n");
}
@ -1718,9 +1718,8 @@ void llama_free(struct llama_context * ctx) {
int llama_model_quantize(
const char * fname_inp,
const char * fname_out,
int itype,
int qk) {
if (!llama_model_quantize_internal(fname_inp, fname_out, itype, qk)) {
int itype) {
if (!llama_model_quantize_internal(fname_inp, fname_out, itype)) {
fprintf(stderr, "%s: failed to quantize\n", __func__);
return 1;
}
@ -1803,9 +1802,9 @@ llama_token llama_sample_top_p_top_k(
const llama_token * last_n_tokens_data,
int last_n_tokens_size,
int top_k,
double top_p,
double temp,
double repeat_penalty) {
float top_p,
float temp,
float repeat_penalty) {
const int64_t t_start_sample_us = ggml_time_us();
llama_token result = 0;
@ -1836,11 +1835,11 @@ void llama_print_timings(struct llama_context * ctx) {
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: 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);
fprintf(stderr, "%s: load time = %8.2f ms\n", __func__, ctx->t_load_us / 1000.0);
fprintf(stderr, "%s: sample time = %8.2f ms / %5d runs (%8.2f ms per run)\n", __func__, 1e-3 * ctx->t_sample_us, n_sample, 1e-3 * 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-3 * ctx->t_p_eval_us, n_p_eval, 1e-3 * 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-3 * ctx->t_eval_us, n_eval, 1e-3 * ctx->t_eval_us / n_eval);
fprintf(stderr, "%s: total time = %8.2f ms\n", __func__, (t_end_us - ctx->t_start_us)/1000.0);
}
void llama_reset_timings(struct llama_context * ctx) {