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

fix spacing

Browse source
This commit is contained in:
ngxson 2024-02-28 22:06:21 +01:00
parent e2992ea332
commit 51381f8f5d
1 changed files with 51 additions and 45 deletions
Download patch file Download diff file Expand all files Collapse all files

50
examples/server/server.cpp
View file

@ -33,8 +33,7 @@
using json = nlohmann::json;
struct server_params
{
struct server_params {
std::string hostname = "127.0.0.1";
std::vector<std::string> api_keys;
std::string public_path = "examples/server/public";
@ -177,8 +176,7 @@ struct server_slot {
generated_token_probs.clear();
for (slot_image & img : images)
{
for (slot_image & img : images) {
free(img.image_embedding);
if (img.img_data) {
clip_image_u8_free(img.img_data);
@ -190,19 +188,15 @@ struct server_slot {
}
bool has_budget(gpt_params &global_params) {
if (params.n_predict == -1 && global_params.n_predict == -1)
{
if (params.n_predict == -1 && global_params.n_predict == -1) {
return true; // limitless
}
n_remaining = -1;
if (params.n_predict != -1)
{
if (params.n_predict != -1) {
n_remaining = params.n_predict - n_decoded;
}
else if (global_params.n_predict != -1)
{
} else if (global_params.n_predict != -1) {
n_remaining = global_params.n_predict - n_decoded;
}
@ -218,8 +212,7 @@ struct server_slot {
}
void add_token_string(const completion_token_output &token) {
if (command == RELEASE)
{
if (command == RELEASE) {
return;
}
cache_tokens.push_back(token.tok);
@ -1227,9 +1220,7 @@ struct llama_server_context
const int n_embd = llama_n_embd(model);
if (!params.embedding)
{
LOG_WARNING("embedding disabled", {
{"params.embedding", params.embedding},
});
LOG_WARNING("embedding disabled", {{"params.embedding", params.embedding}});
res.result_json = json
{
{"embedding", std::vector<float>(n_embd, 0.0f)},
@ -1241,7 +1232,7 @@ struct llama_server_context
std::vector<float> embedding(data, data + n_embd);
res.result_json = json
{
{"embedding", embedding },
{"embedding", embedding},
};
}
queue_results.send(res);
@ -1329,7 +1320,17 @@ struct llama_server_context
}
const int n_embd = llama_n_embd(model);
llama_batch batch_img = { n_eval, nullptr, (img.image_embedding + i * n_embd), nullptr, nullptr, nullptr, nullptr, slot.n_past, 1, 0, };
llama_batch batch_img = {
n_eval,
nullptr,
(img.image_embedding + i * n_embd),
nullptr,
nullptr,
nullptr,
nullptr,
slot.n_past,
1, 0
};
if (llama_decode(ctx, batch_img))
{
LOG_TEE("%s : failed to eval image\n", __func__);
@ -1714,8 +1715,13 @@ struct llama_server_context
const int n_block_size = n_left / 2;
const int erased_blocks = (slot.n_prompt_tokens - slot.params.n_keep - n_block_size) / n_block_size;
std::vector<llama_token> new_tokens(prompt_tokens.begin(), prompt_tokens.begin() + slot.params.n_keep);
new_tokens.insert(new_tokens.end(), prompt_tokens.begin() + slot.params.n_keep + erased_blocks * n_block_size, prompt_tokens.end());
std::vector<llama_token> new_tokens(
prompt_tokens.begin(),
prompt_tokens.begin() + slot.params.n_keep);
new_tokens.insert(
new_tokens.end(),
prompt_tokens.begin() + slot.params.n_keep + erased_blocks * n_block_size,
prompt_tokens.end());
LOG_VERBOSE("input truncated", {
{"n_ctx", slot.n_ctx},
@ -1843,8 +1849,8 @@ struct llama_server_context
if (has_images && !ingest_images(slot, n_batch))
{
LOG_ERROR("failed processing images", {
"slot_id", slot.id,
"task_id", slot.task_id,
{"slot_id", slot.id},
{"task_id", slot.task_id},
});
// FIXME @phymbert: to be properly tested
// early returning without changing the slot state will block the slot for ever