Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-17 08:19:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	CMakeLists.txt
#	Makefile
#	README.md
#	common/common.cpp
#	requirements/requirements-convert-hf-to-gguf-update.txt
#	requirements/requirements-convert-hf-to-gguf.txt
#	requirements/requirements-convert.txt
#	tests/CMakeLists.txt
#	tests/test-json-schema-to-grammar.cpp
This commit is contained in:
Concedo
2024-05-09 15:13:34 +08:00
parent caf9f21888 4426e2987b
commit d084f78faa
48 changed files with 3786 additions and 1438 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/server/README.md
+1 -1
View File
@@ -331,7 +331,7 @@ Notice that each `probs` is an array of length `n_probs`.
`content`: Set the text to tokenize.
Note that a special `BOS` token is never inserted.
`add_special`: Boolean indicating if special tokens, i.e. `BOS`, should be inserted. Default: `false`
- **POST** `/detokenize`: Convert tokens to text.
examples/server/public/favicon.ico
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 4.0 KiB

examples/server/server.cpp
+39 -36
View File
@@ -13,6 +13,8 @@
// increase max payload length to allow use of larger context size
#define CPPHTTPLIB_FORM_URL_ENCODED_PAYLOAD_MAX_LENGTH 1048576
#include "httplib.h"
// Change JSON_ASSERT from assert() to GGML_ASSERT:
#define JSON_ASSERT GGML_ASSERT
#include "json.hpp"
// auto generated files (update with ./deps.sh)
@@ -860,7 +862,7 @@ struct server_context {
slot.sparams.min_keep = json_value(data, "min_keep", default_sparams.min_keep);
// process "json_schema" and "grammar"
if (data.contains("json_schema") && !data["json_schema"].is_null() && data.contains("grammar") && !data["grammar"].is_null()) {
if (data.contains("json_schema") && !data.at("json_schema").is_null() && data.contains("grammar") && !data.at("grammar").is_null()) {
send_error(task, "Either \"json_schema\" or \"grammar\" can be specified, but not both", ERROR_TYPE_INVALID_REQUEST);
return false;
} else if (data.contains("json_schema") && !data.contains("grammar")) {
@@ -1513,7 +1515,7 @@ struct server_context {
// add subtasks
for (int i = 0; i < prompt_count; i++) {
json subtask_data = multiprompt_task.data;
subtask_data["prompt"] = subtask_data["prompt"][i];
subtask_data["prompt"] = subtask_data.at("prompt")[i];
// subtasks inherit everything else (infill mode, embedding mode, etc.)
request_completion(subtask_ids[i], id_multi, subtask_data, multiprompt_task.infill, multiprompt_task.embedding);
@@ -1533,7 +1535,7 @@ struct server_context {
}
if (task.data.contains("system_prompt")) {
system_prompt_set(task.data["system_prompt"]);
system_prompt_set(task.data.at("system_prompt"));
for (server_slot & slot : slots) {
slot.n_past = 0;
@@ -1645,7 +1647,7 @@ struct server_context {
} break;
case SERVER_TASK_TYPE_SLOT_SAVE:
{
int id_slot = task.data["id_slot"];
int id_slot = task.data.at("id_slot");
server_slot * slot = get_slot(id_slot);
if (slot == nullptr) {
send_error(task, "Invalid slot ID", ERROR_TYPE_INVALID_REQUEST);
@@ -1655,8 +1657,8 @@ struct server_context {
const size_t token_count = slot->cache_tokens.size();
const int64_t t_start = ggml_time_us();
std::string filename = task.data["filename"];
std::string filepath = task.data["filepath"];
std::string filename = task.data.at("filename");
std::string filepath = task.data.at("filepath");
const size_t nwrite = llama_state_seq_save_file(ctx, filepath.c_str(), slot->id + 1, slot->cache_tokens.data(), token_count);
@@ -1680,7 +1682,7 @@ struct server_context {
} break;
case SERVER_TASK_TYPE_SLOT_RESTORE:
{
int id_slot = task.data["id_slot"];
int id_slot = task.data.at("id_slot");
server_slot * slot = get_slot(id_slot);
if (slot == nullptr) {
send_error(task, "Invalid slot ID", ERROR_TYPE_INVALID_REQUEST);
@@ -1689,8 +1691,8 @@ struct server_context {
const int64_t t_start = ggml_time_us();
std::string filename = task.data["filename"];
std::string filepath = task.data["filepath"];
std::string filename = task.data.at("filename");
std::string filepath = task.data.at("filepath");
slot->cache_tokens.resize(slot->n_ctx);
size_t token_count = 0;
@@ -1722,7 +1724,7 @@ struct server_context {
} break;
case SERVER_TASK_TYPE_SLOT_ERASE:
{
int id_slot = task.data["id_slot"];
int id_slot = task.data.at("id_slot");
server_slot * slot = get_slot(id_slot);
if (slot == nullptr) {
send_error(task, "Invalid slot ID", ERROR_TYPE_INVALID_REQUEST);
@@ -3137,8 +3139,8 @@ int main(int argc, char ** argv) {
server_task_result result = ctx_server.queue_results.recv(task.id);
ctx_server.queue_results.remove_waiting_task_id(task.id);
const int n_idle_slots = result.data["idle"];
const int n_processing_slots = result.data["processing"];
const int n_idle_slots = result.data.at("idle");
const int n_processing_slots = result.data.at("processing");
json health = {
{"status", "ok"},
@@ -3148,7 +3150,7 @@ int main(int argc, char ** argv) {
res.status = 200; // HTTP OK
if (sparams.slots_endpoint && req.has_param("include_slots")) {
health["slots"] = result.data["slots"];
health["slots"] = result.data.at("slots");
}
if (n_idle_slots == 0) {
@@ -3192,7 +3194,7 @@ int main(int argc, char ** argv) {
server_task_result result = ctx_server.queue_results.recv(task.id);
ctx_server.queue_results.remove_waiting_task_id(task.id);
res.set_content(result.data["slots"].dump(), "application/json");
res.set_content(result.data.at("slots").dump(), "application/json");
res.status = 200; // HTTP OK
};
@@ -3219,32 +3221,32 @@ int main(int argc, char ** argv) {
json data = result.data;
const uint64_t n_prompt_tokens_processed = data["n_prompt_tokens_processed"];
const uint64_t t_prompt_processing = data["t_prompt_processing"];
const uint64_t n_prompt_tokens_processed = data.at("n_prompt_tokens_processed");
const uint64_t t_prompt_processing = data.at("t_prompt_processing");
const uint64_t n_tokens_predicted = data["n_tokens_predicted"];
const uint64_t t_tokens_generation = data["t_tokens_generation"];
const uint64_t n_tokens_predicted = data.at("n_tokens_predicted");
const uint64_t t_tokens_generation = data.at("t_tokens_generation");
const int32_t kv_cache_used_cells = data["kv_cache_used_cells"];
const int32_t kv_cache_used_cells = data.at("kv_cache_used_cells");
// metrics definition: https://prometheus.io/docs/practices/naming/#metric-names
json all_metrics_def = json {
{"counter", {{
{"name", "prompt_tokens_total"},
{"help", "Number of prompt tokens processed."},
{"value", (uint64_t) data["n_prompt_tokens_processed_total"]}
{"value", (uint64_t) data.at("n_prompt_tokens_processed_total")}
}, {
{"name", "prompt_seconds_total"},
{"help", "Prompt process time"},
{"value", (uint64_t) data["t_prompt_processing_total"] / 1.e3}
{"value", (uint64_t) data.at("t_prompt_processing_total") / 1.e3}
}, {
{"name", "tokens_predicted_total"},
{"help", "Number of generation tokens processed."},
{"value", (uint64_t) data["n_tokens_predicted_total"]}
{"value", (uint64_t) data.at("n_tokens_predicted_total")}
}, {
{"name", "tokens_predicted_seconds_total"},
{"help", "Predict process time"},
{"value", (uint64_t) data["t_tokens_generation_total"] / 1.e3}
{"value", (uint64_t) data.at("t_tokens_generation_total") / 1.e3}
}}},
{"gauge", {{
{"name", "prompt_tokens_seconds"},
@@ -3261,15 +3263,15 @@ int main(int argc, char ** argv) {
},{
{"name", "kv_cache_tokens"},
{"help", "KV-cache tokens."},
{"value", (uint64_t) data["kv_cache_tokens_count"]}
{"value", (uint64_t) data.at("kv_cache_tokens_count")}
},{
{"name", "requests_processing"},
{"help", "Number of request processing."},
{"value", (uint64_t) data["processing"]}
{"value", (uint64_t) data.at("processing")}
},{
{"name", "requests_deferred"},
{"help", "Number of request deferred."},
{"value", (uint64_t) data["deferred"]}
{"value", (uint64_t) data.at("deferred")}
}}}
};
@@ -3280,8 +3282,8 @@ int main(int argc, char ** argv) {
const auto & metrics_def = el.value();
for (const auto & metric_def : metrics_def) {
const std::string name = metric_def["name"];
const std::string help = metric_def["help"];
const std::string name = metric_def.at("name");
const std::string help = metric_def.at("help");
auto value = json_value(metric_def, "value", 0.);
prometheus << "# HELP llamacpp:" << name << " " << help << "\n"
@@ -3290,7 +3292,7 @@ int main(int argc, char ** argv) {
}
}
const int64_t t_start = data["t_start"];
const int64_t t_start = data.at("t_start");
res.set_header("Process-Start-Time-Unix", std::to_string(t_start));
res.set_content(prometheus.str(), "text/plain; version=0.0.4");
@@ -3299,7 +3301,7 @@ int main(int argc, char ** argv) {
const auto handle_slots_save = [&ctx_server, &res_error, &sparams](const httplib::Request & req, httplib::Response & res, int id_slot) {
json request_data = json::parse(req.body);
std::string filename = request_data["filename"];
std::string filename = request_data.at("filename");
if (!validate_file_name(filename)) {
res_error(res, format_error_response("Invalid filename", ERROR_TYPE_INVALID_REQUEST));
return;
@@ -3329,7 +3331,7 @@ int main(int argc, char ** argv) {
const auto handle_slots_restore = [&ctx_server, &res_error, &sparams](const httplib::Request & req, httplib::Response & res, int id_slot) {
json request_data = json::parse(req.body);
std::string filename = request_data["filename"];
std::string filename = request_data.at("filename");
if (!validate_file_name(filename)) {
res_error(res, format_error_response("Invalid filename", ERROR_TYPE_INVALID_REQUEST));
return;
@@ -3648,7 +3650,8 @@ int main(int argc, char ** argv) {
std::vector<llama_token> tokens;
if (body.count("content") != 0) {
tokens = ctx_server.tokenize(body["content"], false);
const bool add_special = json_value(body, "add_special", false);
tokens = ctx_server.tokenize(body.at("content"), add_special);
}
const json data = format_tokenizer_response(tokens);
return res.set_content(data.dump(), "application/json; charset=utf-8");
@@ -3660,7 +3663,7 @@ int main(int argc, char ** argv) {
std::string content;
if (body.count("tokens") != 0) {
const std::vector<llama_token> tokens = body["tokens"];
const std::vector<llama_token> tokens = body.at("tokens");
content = tokens_to_str(ctx_server.ctx, tokens.cbegin(), tokens.cend());
}
@@ -3683,10 +3686,10 @@ int main(int argc, char ** argv) {
json prompt;
if (body.count("input") != 0) {
is_openai = true;
prompt = body["input"];
prompt = body.at("input");
} else if (body.count("content") != 0) {
// with "content", we only support single prompt
prompt = std::vector<std::string>{body["content"]};
prompt = std::vector<std::string>{body.at("content")};
} else {
res_error(res, format_error_response("\"input\" or \"content\" must be provided", ERROR_TYPE_INVALID_REQUEST));
return;
@@ -3705,7 +3708,7 @@ int main(int argc, char ** argv) {
if (!result.error) {
if (result.data.count("results")) {
// result for multi-task
responses = result.data["results"];
responses = result.data.at("results");
} else {
// result for single task
responses = std::vector<json>{result.data};
examples/server/tests/features/server.feature
+13 -1
View File
@@ -7,6 +7,7 @@ Feature: llama.cpp server
And a model file tinyllamas/stories260K.gguf from HF repo ggml-org/models
And a model file test-model.gguf
And a model alias tinyllama-2
And BOS token is 1
And 42 as server seed
# KV Cache corresponds to the total amount of tokens
# that can be stored across all independent sequences: #4130
@@ -91,7 +92,18 @@ Feature: llama.cpp server
"""
What is the capital of France ?
"""
Then tokens can be detokenize
Then tokens can be detokenized
And tokens do not begin with BOS
Scenario: Tokenize w/ BOS
Given adding special tokens
When tokenizing:
"""
What is the capital of Germany?
"""
Then tokens begin with BOS
Given first token is removed
Then tokens can be detokenized
Scenario: Models available
Given available models
examples/server/tests/features/steps/steps.py
+33 -5
View File
@@ -376,6 +376,11 @@ def step_seed(context, seed):
context.seed.append(seed)
@step('BOS token is {bos:d}')
def step_bos_token(context, bos):
context.bos = bos
@step('a prefix prompt')
def step_prompt_prefix(context):
context.prompt_prefix = context_text(context)
@@ -656,21 +661,29 @@ async def all_embeddings_are_generated(context):
assert_embeddings(context.tasks_result.pop().pop())
@step('adding special tokens')
def step_tokenize_set_add_special(context):
context.tokenize_add_special = True
@step('tokenizing')
@async_run_until_complete
async def step_tokenize(context):
context.tokenized_text = context_text(context)
async with aiohttp.ClientSession() as session:
tokenize_args = {
"content": context.tokenized_text,
}
if getattr(context, 'tokenize_add_special', None) is not None:
tokenize_args['add_special'] = context.tokenize_add_special
async with session.post(f'{context.base_url}/tokenize',
json={
"content": context.tokenized_text,
}) as response:
json=tokenize_args) as response:
assert response.status == 200
tokenize_json = await response.json()
context.tokens = tokenize_json['tokens']
@step('tokens can be detokenize')
@step('tokens can be detokenized')
@async_run_until_complete
async def step_detokenize(context):
assert len(context.tokens) > 0
@@ -685,6 +698,21 @@ async def step_detokenize(context):
assert context.tokenized_text == detokenize_json['content'].strip()
@step('tokens begin with BOS')
def step_strings_for_tokenization(context):
assert context.tokens[0] == context.bos
@step('tokens do not begin with BOS')
def step_strings_for_tokenization(context):
assert context.tokens[0] != context.bos
@step('first token is removed')
def step_strings_for_tokenization(context):
context.tokens = context.tokens[1:]
@step('an OPTIONS request is sent from {origin}')
@async_run_until_complete
async def step_options_request(context, origin):
@@ -911,7 +939,7 @@ async def oai_chat_completions(user_prompt,
while event_received:
event_received = False
async for line_in_bytes in response.content:
line = line_in_bytes.decode('utf8')
line = line_in_bytes.decode('utf-8')
line = line.rstrip('\n').rstrip('\r')
if line == '':
continue
examples/server/themes/README.md
+5
View File
@@ -0,0 +1,5 @@
# LLaMA.cpp Server Wild Theme
Simple themes directory of sample "public" directories. To try any of these add --path to your run like `server --path=wild`.
![image](wild/wild.png)
examples/server/themes/buttons-top/README.md
+7
View File
@@ -0,0 +1,7 @@
# LLaMA.cpp Server Buttons Top Theme
Simple tweaks to the UI. Chat buttons at the top of the page instead of bottom so you can hit Stop instead of chasing it down the page.
To use simply run server with `--path=themes/buttons_top`
![image](buttons_top.png)
examples/server/themes/buttons-top/buttons_top.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 117 KiB

examples/server/themes/buttons-top/favicon.ico
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 4.0 KiB

examples/server/themes/buttons-top/index.html
+1057
View File
File diff suppressed because it is too large Load Diff
examples/server/themes/wild/README.md
+5
View File
@@ -0,0 +1,5 @@
# LLaMA.cpp Server Wild Theme
Simple tweaks to the UI. To use simply run server with `--path=themes/wild`
![image](wild.png)
examples/server/themes/wild/favicon.ico
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 4.0 KiB

examples/server/themes/wild/index.html
+1061
View File
File diff suppressed because it is too large Load Diff
examples/server/themes/wild/llama_cpp.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 75 KiB

examples/server/themes/wild/llamapattern.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 254 KiB

examples/server/themes/wild/wild.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 485 KiB

examples/server/utils.hpp
+17 -15
View File
@@ -3,6 +3,8 @@
#include "llama.h"
#include "common.h"
// Change JSON_ASSERT from assert() to GGML_ASSERT:
#define JSON_ASSERT GGML_ASSERT
#include "json.hpp"
#include <string>
@@ -49,18 +51,18 @@ extern bool server_log_json;
#define LOG_WARNING(MSG, ...) server_log("WARN", __func__, __LINE__, MSG, __VA_ARGS__)
#define LOG_INFO( MSG, ...) server_log("INFO", __func__, __LINE__, MSG, __VA_ARGS__)
static inline void server_log(const char *level, const char *function, int line, const char *message, const nlohmann::ordered_json &extra);
static inline void server_log(const char * level, const char * function, int line, const char * message, const json & extra);
template <typename T>
static T json_value(const json &body, const std::string &key, const T &default_value) {
static T json_value(const json & body, const std::string & key, const T & default_value) {
// Fallback null to default value
if (body.contains(key) && !body.at(key).is_null()){
if (body.contains(key) && !body.at(key).is_null()) {
try {
return body.value(key, default_value);
}
catch (nlohmann::json_abi_v3_11_3::detail::type_error const&){
std::string message = "Wrong type supplied for parameter '" + key + "'. Expected '" + typeid(default_value).name() + "', using default value.";
server_log("WARN", __func__, __LINE__, message.c_str(), body);
return body.at(key);
} catch (NLOHMANN_JSON_NAMESPACE::detail::type_error const &) {
std::stringstream ss;
ss << "Wrong type supplied for parameter '" << key << "'. Expected '" << json(default_value).type_name() << "', using default value.";
LOG_WARNING(ss.str().c_str(), body);
return default_value;
}
} else {
@@ -68,16 +70,16 @@ static T json_value(const json &body, const std::string &key, const T &default_v
}
}
static inline void server_log(const char *level, const char *function, int line, const char *message, const nlohmann::ordered_json &extra) {
static inline void server_log(const char * level, const char * function, int line, const char * message, const json & extra) {
std::stringstream ss_tid;
ss_tid << std::this_thread::get_id();
json log = nlohmann::ordered_json{
json log = json{
{"tid", ss_tid.str()},
{"timestamp", time(nullptr)},
};
if (server_log_json) {
log.merge_patch( {
log.merge_patch({
{"level", level},
{"function", function},
{"line", line},
@@ -98,7 +100,7 @@ static inline void server_log(const char *level, const char *function, int line,
}
std::stringstream ss;
ss << buf << " |";
for (const auto& el : log.items())
for (const auto & el : log.items())
{
const std::string value = el.value().dump(-1, ' ', false, json::error_handler_t::replace);
ss << " " << el.key() << "=" << value;
@@ -373,11 +375,11 @@ static json oaicompat_completion_params_parse(
llama_params["top_p"] = json_value(body, "top_p", 1.0);
// Apply chat template to the list of messages
llama_params["prompt"] = format_chat(model, chat_template, body["messages"]);
llama_params["prompt"] = format_chat(model, chat_template, body.at("messages"));
// Handle "stop" field
if (body.contains("stop") && body["stop"].is_string()) {
llama_params["stop"] = json::array({body["stop"].get<std::string>()});
if (body.contains("stop") && body.at("stop").is_string()) {
llama_params["stop"] = json::array({body.at("stop").get<std::string>()});
} else {
llama_params["stop"] = json_value(body, "stop", json::array());
}