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

Merge branch 'master' into gg/llama-kv-cache

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2025-02-06 10:04:33 +02:00
commit 0f1c1cab2c
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
83 changed files with 3593 additions and 1410 deletions
Download patch file Download diff file Expand all files Collapse all files

22
examples/server/README.md
View file

@ -1128,6 +1128,7 @@ curl http://localhost:8080/v1/chat/completions \
- Hermes 2/3, Qwen 2.5
- Mistral Nemo
- Firefunction v2
- Command R7B
- DeepSeek R1 (WIP / seems reluctant to call any tools?)
<details>
@ -1202,21 +1203,28 @@ curl http://localhost:8080/v1/chat/completions \
```shell
# Native support:
llama-server --jinja -fa -hf bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M
llama-server --jinja -fa -hf bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M
llama-server --jinja -fa -hf bartowski/Llama-3.2-3B-Instruct-GGUF:Q6_K
llama-server --jinja -fa -hf bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q6_K_L
llama-server --jinja -fa -hf bartowski/functionary-small-v3.2-GGUF:Q4_K_M
llama-server --jinja -fa -hf bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M \
--chat-template-file <( python scripts/get_chat_template.py NousResearch/Hermes-2-Pro-Llama-3-8B )
llama-server --jinja -fa -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_K_M
# Native support requires the right template for these GGUFs:
llama-server --jinja -fa -hf bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M \
--chat-template-file <( python scripts/get_chat_template.py NousResearch/Hermes-2-Pro-Llama-3-8B tool_use )
llama-server --jinja -fa -hf bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M \
--chat-template-file <( python scripts/get_chat_template.py NousResearch/Hermes-3-Llama-3.1-8B tool_use )
llama-server --jinja -fa -hf bartowski/firefunction-v2-GGUF -hff firefunction-v2-IQ1_M.gguf \
--chat-template-file <( python scripts/get_chat_template.py fireworks-ai/firellama-3-firefunction-v2 )
--chat-template-file <( python scripts/get_chat_template.py fireworks-ai/llama-3-firefunction-v2 tool_use )
llama-server --jinja -fa -hf bartowski/c4ai-command-r7b-12-2024-GGUF:Q6_K_L \
--chat-template-file <( python scripts/get_chat_template.py CohereForAI/c4ai-command-r7b-12-2024 tool_use )
# Generic format support
llama-server --jinja -fa -hf bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M
llama-server --jinja -fa -hf bartowski/gemma-2-2b-it-GGUF:Q4_K_M
llama-server --jinja -fa -hf bartowski/phi-4-GGUF:Q4_0
llama-server --jinja -fa -hf bartowski/gemma-2-2b-it-GGUF:Q8_0
llama-server --jinja -fa -hf bartowski/c4ai-command-r-v01-GGUF:Q2_K
```
- Test in CLI:

BIN
examples/server/public/index.html.gz
View file

Binary file not shown.

64
examples/server/server.cpp
View file

@ -131,6 +131,11 @@ struct slot_params {
lora.push_back({{"id", i}, {"scale", this->lora[i].scale}});
}
std::vector<std::string> grammar_trigger_words;
for (const auto & trigger : sampling.grammar_trigger_words) {
grammar_trigger_words.push_back(trigger.word);
}
return json {
{"n_predict", n_predict}, // Server configured n_predict
{"seed", sampling.seed},
@ -165,8 +170,9 @@ struct slot_params {
{"n_probs", sampling.n_probs},
{"min_keep", sampling.min_keep},
{"grammar", sampling.grammar},
// {"grammar_trigger_words", sampling.grammar_trigger_words},
{"grammar_trigger_words", grammar_trigger_words},
{"grammar_trigger_tokens", sampling.grammar_trigger_tokens},
{"preserved_tokens", sampling.preserved_tokens},
{"samplers", samplers},
{"speculative.n_max", speculative.n_max},
{"speculative.n_min", speculative.n_min},
@ -363,12 +369,26 @@ struct server_task {
if (ids.size() == 1) {
LOG_DBG("Grammar trigger token: %d (`%s`)\n", ids[0], trigger.word.c_str());
params.sampling.grammar_trigger_tokens.push_back(ids[0]);
params.sampling.preserved_tokens.insert(ids[0]);
continue;
}
LOG_DBG("Grammar trigger word: `%s`\n", trigger.word.c_str());
params.sampling.grammar_trigger_words.push_back(trigger);
}
}
const auto preserved_tokens = data.find("preserved_tokens");
if (preserved_tokens != data.end()) {
for (const auto & t : *preserved_tokens) {
auto ids = common_tokenize(vocab, t.get<std::string>(), /* add_special= */ false, /* parse_special= */ true);
if (ids.size() == 1) {
LOG_DBG("Preserved token: %d\n", ids[0]);
params.sampling.preserved_tokens.insert(ids[0]);
} else {
// This may happen when using a tool call style meant for a model with special tokens to preserve on a model without said tokens.
LOG_WRN("Not preserved because more than 1 token (wrong chat template override?): %s\n", t.get<std::string>().c_str());
}
}
}
if (params.sampling.grammar_lazy) {
GGML_ASSERT(params.sampling.grammar_trigger_tokens.size() > 0 || params.sampling.grammar_trigger_words.size() > 0);
}
@ -695,19 +715,19 @@ struct server_task_result_cmpl_final : server_task_result {
json to_json_oaicompat_chat() {
std::string finish_reason = "length";
common_chat_msg message;
common_chat_msg msg;
if (stop == STOP_TYPE_WORD || stop == STOP_TYPE_EOS) {
LOG_DBG("Parsing chat message: %s\n", content.c_str());
message = common_chat_parse(content, oaicompat_chat_format);
finish_reason = message.tool_calls.empty() ? "stop" : "tool_calls";
msg = common_chat_parse(content, oaicompat_chat_format);
finish_reason = msg.tool_calls.empty() ? "stop" : "tool_calls";
} else {
message.content = content;
msg.content = content;
}
json tool_calls;
if (!message.tool_calls.empty()) {
if (!msg.tool_calls.empty()) {
tool_calls = json::array();
for (const auto & tc : message.tool_calls) {
for (const auto & tc : msg.tool_calls) {
tool_calls.push_back({
{"type", "function"},
{"function", {
@ -719,14 +739,19 @@ struct server_task_result_cmpl_final : server_task_result {
}
}
json message {
{"content", msg.content},
{"tool_calls", tool_calls},
{"role", "assistant"},
};
if (!msg.tool_plan.empty()) {
message["tool_plan"] = msg.tool_plan;
}
json choice {
{"finish_reason", finish_reason},
{"index", 0},
{"message", json {
{"content", message.content},
{"tool_calls", tool_calls},
{"role", "assistant"},
}},
{"message", message},
};
if (!stream && probs_output.size() > 0) {
@ -2833,8 +2858,7 @@ struct server_context {
server_slot * slot_batched = nullptr;
auto accept_special_token = [&](server_slot & slot, llama_token token) {
const auto & trigger_tokens = slot.params.sampling.grammar_trigger_tokens;
return params_base.special || std::find(trigger_tokens.begin(), trigger_tokens.end(), token) != trigger_tokens.end();
return params_base.special || slot.params.sampling.preserved_tokens.find(token) != slot.params.sampling.preserved_tokens.end();
};
// frist, add sampled tokens from any ongoing sequences
@ -3329,6 +3353,8 @@ static void log_server_request(const httplib::Request & req, const httplib::Resp
return;
}
// reminder: this function is not covered by httplib's exception handler; if someone does more complicated stuff, think about wrapping it in try-catch
LOG_INF("request: %s %s %s %d\n", req.method.c_str(), req.path.c_str(), req.remote_addr.c_str(), res.status);
LOG_DBG("request: %s\n", req.body.c_str());
@ -3415,9 +3441,13 @@ int main(int argc, char ** argv) {
message = "Unknown Exception";
}
json formatted_error = format_error_response(message, ERROR_TYPE_SERVER);
LOG_WRN("got exception: %s\n", formatted_error.dump().c_str());
res_error(res, formatted_error);
try {
json formatted_error = format_error_response(message, ERROR_TYPE_SERVER);
LOG_WRN("got exception: %s\n", formatted_error.dump().c_str());
res_error(res, formatted_error);
} catch (const std::exception & e) {
LOG_ERR("got another exception: %s | while hanlding exception: %s\n", e.what(), message.c_str());
}
});
svr->set_error_handler([&res_error](const httplib::Request &, httplib::Response & res) {

7
examples/server/tests/unit/test_chat_completion.py
View file

@ -13,9 +13,12 @@ def create_server():
@pytest.mark.parametrize(
"model,system_prompt,user_prompt,max_tokens,re_content,n_prompt,n_predicted,finish_reason,jinja,chat_template",
[
(None, "Book", "Hey", 8, "But she couldn't", 69, 8, "length", False, None),
(None, "Book", "Hey", 8, "But she couldn't", 69, 8, "length", True, None),
(None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", False, None),
(None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True, None),
(None, "Book", "What is the best book", 8, "^ blue", 23, 8, "length", True, "This is not a chat template, it is"),
(None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True, None),
(None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True, 'chatml'),
(None, "Book", "What is the best book", 8, "^ blue", 23, 8, "length", True, "This is not a chat template, it is"),
("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length", False, None),
("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length", True, None),
]

104
examples/server/tests/unit/test_tool_call.py
View file

@ -67,8 +67,8 @@ WEATHER_TOOL = {
def do_test_completion_with_required_tool_tiny(template_name: str, tool: dict, argument_key: str | None):
n_predict = 512
global server
n_predict = 512
# server = ServerPreset.stories15m_moe()
server.jinja = True
server.n_predict = n_predict
@ -139,29 +139,49 @@ def test_completion_with_required_tool_tiny_slow(template_name: str, tool: dict,
@pytest.mark.parametrize("tool,argument_key,hf_repo,template_override", [
(TEST_TOOL, "success", "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
(PYTHON_TOOL, "code", "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
(PYTHON_TOOL, "code", "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"),
# Note: gemma-2-2b-it knows itself as "model", not "assistant", so we don't test the ill-suited chatml on it.
(TEST_TOOL, "success", "bartowski/gemma-2-2b-it-GGUF:Q4_K_M", None),
(PYTHON_TOOL, "code", "bartowski/gemma-2-2b-it-GGUF:Q4_K_M", None),
(TEST_TOOL, "success", "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", None),
(PYTHON_TOOL, "code", "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", None),
(PYTHON_TOOL, "code", "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", "chatml"),
(TEST_TOOL, "success", "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", None),
(PYTHON_TOOL, "code", "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", None),
(PYTHON_TOOL, "code", "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", "chatml"),
(TEST_TOOL, "success", "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
(PYTHON_TOOL, "code", "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
(PYTHON_TOOL, "code", "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", "chatml"),
(TEST_TOOL, "success", "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")),
(PYTHON_TOOL, "code", "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")),
(PYTHON_TOOL, "code", "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", "chatml"),
(TEST_TOOL, "success", "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None),
(PYTHON_TOOL, "code", "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None),
(TEST_TOOL, "success", "bartowski/functionary-small-v3.2-GGUF:Q8_0", ("meetkai/functionary-medium-v3.2", None)),
(PYTHON_TOOL, "code", "bartowski/functionary-small-v3.2-GGUF:Q8_0", ("meetkai/functionary-medium-v3.2", None)),
(PYTHON_TOOL, "code", "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", "chatml"),
(TEST_TOOL, "success", "bartowski/functionary-small-v3.2-GGUF:Q4_K_M", ("meetkai/functionary-medium-v3.2", None)),
(PYTHON_TOOL, "code", "bartowski/functionary-small-v3.2-GGUF:Q4_K_M", ("meetkai/functionary-medium-v3.2", None)),
(PYTHON_TOOL, "code", "bartowski/functionary-small-v3.2-GGUF:Q4_K_M", "chatml"),
(TEST_TOOL, "success", "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)),
(PYTHON_TOOL, "code", "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)),
(PYTHON_TOOL, "code", "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", "chatml"),
(TEST_TOOL, "success", "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)),
(PYTHON_TOOL, "code", "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)),
(PYTHON_TOOL, "code", "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", "chatml"),
# TODO: fix these
# (TEST_TOOL, "success", "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
# (PYTHON_TOOL, "code", "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
])
def test_completion_with_required_tool_real_model(tool: dict, argument_key: str | None, hf_repo: str, template_override: Tuple[str, str | None] | None):
def test_completion_with_required_tool_real_model(tool: dict, argument_key: str | None, hf_repo: str, template_override: str | Tuple[str, str | None] | None):
global server
n_predict = 512
server.n_slots = 1
server.jinja = True
@ -169,10 +189,12 @@ def test_completion_with_required_tool_real_model(tool: dict, argument_key: str
server.n_predict = n_predict
server.model_hf_repo = hf_repo
server.model_hf_file = None
if template_override:
if isinstance(template_override, tuple):
(template_hf_repo, template_variant) = template_override
server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja"
assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template."
elif isinstance(template_override, str):
server.chat_template = template_override
server.start(timeout_seconds=TIMEOUT_SERVER_START)
res = server.make_request("POST", "/chat/completions", data={
"max_tokens": n_predict,
@ -251,33 +273,55 @@ def test_completion_without_tool_call_slow(template_name: str, n_predict: int, t
@pytest.mark.slow
@pytest.mark.parametrize("hf_repo,template_override", [
("bartowski/c4ai-command-r7b-12-2024-GGUF:Q4_K_M", ("CohereForAI/c4ai-command-r7b-12-2024", "tool_use")),
("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
("bartowski/gemma-2-2b-it-GGUF:Q4_K_M", None),
("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"),
("bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", None),
("bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", "chatml"),
("bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", None),
("bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
("bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")),
("bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", "chatml"),
("bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
("bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", "chatml"),
("bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")),
("bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", "chatml"),
("bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None),
("bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", "chatml"),
("bartowski/functionary-small-v3.2-GGUF:Q8_0", ("meetkai/functionary-medium-v3.2", None)),
("bartowski/functionary-small-v3.2-GGUF:Q8_0", "chatml"),
("bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)),
("bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", "chatml"),
# Note: gemma-2-2b-it knows itself as "model", not "assistant", so we don't test the ill-suited chatml on it.
("bartowski/gemma-2-2b-it-GGUF:Q4_K_M", None),
# ("bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)),
# ("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
])
def test_weather_tool_call(hf_repo: str, template_override: Tuple[str, str | None] | None):
def test_weather(hf_repo: str, template_override: Tuple[str, str | None] | None):
global server
n_predict = 512
server.n_slots = 1
server.jinja = True
server.n_ctx = 8192
server.n_predict = 512
server.n_predict = n_predict
server.model_hf_repo = hf_repo
server.model_hf_file = None
if template_override:
if isinstance(template_override, tuple):
(template_hf_repo, template_variant) = template_override
server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja"
assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template."
elif isinstance(template_override, str):
server.chat_template = template_override
server.start(timeout_seconds=TIMEOUT_SERVER_START)
res = server.make_request("POST", "/chat/completions", data={
"max_tokens": 256,
"max_tokens": n_predict,
"messages": [
{"role": "user", "content": "What is the weather in Istanbul?"},
],
@ -298,19 +342,39 @@ def test_weather_tool_call(hf_repo: str, template_override: Tuple[str, str | Non
@pytest.mark.slow
@pytest.mark.parametrize("expected_arguments_override,hf_repo,template_override", [
(None, "bartowski/gemma-2-2b-it-GGUF:Q4_K_M", None),
(None, "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", None),
(None, "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", "chatml"),
(None, "bartowski/functionary-small-v3.2-GGUF:Q8_0", ("meetkai-functionary-medium-v3.2", None)),
('{"code":"print("}', "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
(None, "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", ("meta-llama-Llama-3.2-3B-Instruct", None)),
(None, "bartowski/functionary-small-v3.2-GGUF:Q8_0", "chatml"),
(None, "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
('{"code":"print("}', "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"),
('{"code":"print("}', "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", ("meta-llama-Llama-3.2-3B-Instruct", None)),
(None, "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", "chatml"),
('{"code":"print("}', "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", ("meta-llama-Llama-3.2-3B-Instruct", None)),
('{"code":"print("}', "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", "chatml"),
(None, "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", None),
(None, "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
(None, "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", ("NousResearch-Hermes-3-Llama-3.1-8B", "tool_use")),
(None, "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", "chatml"),
(None, "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
(None, "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", "chatml"),
(None, "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", ("NousResearch-Hermes-3-Llama-3.1-8B", "tool_use")),
(None, "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", "chatml"),
(None, "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None),
(None, "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", "chatml"),
# Note: gemma-2-2b-it knows itself as "model", not "assistant", so we don't test the ill-suited chatml on it.
(None, "bartowski/gemma-2-2b-it-GGUF:Q4_K_M", None),
# (None, "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
])
def test_hello_world_tool_call(expected_arguments_override: str | None, hf_repo: str, template_override: Tuple[str, str | None] | None):
def test_hello_world_tool_call(expected_arguments_override: str | None, hf_repo: str, template_override: str | Tuple[str, str | None] | None):
global server
server.n_slots = 1
server.jinja = True
@ -318,10 +382,12 @@ def test_hello_world_tool_call(expected_arguments_override: str | None, hf_repo:
server.n_predict = 128
server.model_hf_repo = hf_repo
server.model_hf_file = None
if template_override:
if isinstance(template_override, tuple):
(template_hf_repo, template_variant) = template_override
server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja"
assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template."
elif isinstance(template_override, str):
server.chat_template = template_override
server.start(timeout_seconds=TIMEOUT_SERVER_START)
res = server.make_request("POST", "/chat/completions", data={
"max_tokens": 256,

5
examples/server/utils.hpp
View file

@ -5,10 +5,6 @@
#include "llama.h"
#include "common/base64.hpp"
#ifndef NDEBUG
// crash the server in debug mode, otherwise send an http 500 error
#define CPPHTTPLIB_NO_EXCEPTIONS 1
#endif
// increase max payload length to allow use of larger context size
#define CPPHTTPLIB_FORM_URL_ENCODED_PAYLOAD_MAX_LENGTH 1048576
#include "httplib.h"
@ -662,6 +658,7 @@ static json oaicompat_completion_params_parse(
});
}
llama_params["grammar_triggers"] = grammar_triggers;
llama_params["preserved_tokens"] = chat_params.preserved_tokens;
for (const auto & stop : chat_params.additional_stops) {
llama_params["stop"].push_back(stop);
}

2
examples/server/webui/index.html
View file

@ -154,8 +154,6 @@
placeholder="Type a message (Shift+Enter to add a new line)"
v-model="inputMsg"
@keydown.enter.exact.prevent="sendMessage"
@keydown.enter.shift.exact.prevent="inputMsg += '\n'"
:disabled="isGenerating"
id="msg-input"
dir="auto"
></textarea>

5
examples/server/webui/src/main.js
View file

@ -468,7 +468,10 @@ const mainApp = createApp({
URL.revokeObjectURL(url);
},
async sendMessage() {
if (!this.inputMsg) return;
// prevent sending empty message
// also allow typing the message while generating, but does not allow sending it (to match UX/UI behavior of other chat apps)
if (!this.inputMsg || this.isGenerating) return;
const currConvId = this.viewingConvId;
StorageUtils.appendMsg(currConvId, {