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

Add Jinja template support (#11016)

Browse source 
* Copy minja from 58f0ca6dd7

* Add --jinja and --chat-template-file flags

* Add missing <optional> include

* Avoid print in get_hf_chat_template.py

* No designated initializers yet

* Try and work around msvc++ non-macro max resolution quirk

* Update test_chat_completion.py

* Wire LLM_KV_TOKENIZER_CHAT_TEMPLATE_N in llama_model_chat_template

* Refactor test-chat-template

* Test templates w/ minja

* Fix deprecation

* Add --jinja to llama-run

* Update common_chat_format_example to use minja template wrapper

* Test chat_template in e2e test

* Update utils.py

* Update test_chat_completion.py

* Update run.cpp

* Update arg.cpp

* Refactor common_chat_* functions to accept minja template + use_jinja option

* Attempt to fix linkage of LLAMA_CHATML_TEMPLATE

* Revert LLAMA_CHATML_TEMPLATE refactor

* Normalize newlines in test-chat-templates for windows tests

* Forward decl minja::chat_template to avoid eager json dep

* Flush stdout in chat template before potential crash

* Fix copy elision warning

* Rm unused optional include

* Add missing optional include to server.cpp

* Disable jinja test that has a cryptic windows failure

* minja: fix vigogne (https://github.com/google/minja/pull/22)

* Apply suggestions from code review

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Finish suggested renamings

* Move chat_templates inside server_context + remove mutex

* Update --chat-template-file w/ recent change to --chat-template

* Refactor chat template validation

* Guard against missing eos/bos tokens (null token otherwise throws in llama_vocab::impl::token_get_attr)

* Warn against missing eos / bos tokens when jinja template references them

* rename: common_chat_template[s]

* reinstate assert on chat_templates.template_default

* Update minja to b8437df626

* Update minja to https://github.com/google/minja/pull/25

* Update minja from https://github.com/google/minja/pull/27

* rm unused optional header

---------

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Olivier Chafik 2025-01-21 13:18:51 +00:00 • committed by GitHub
parent e28245f35f
commit 6171c9d258
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
22 changed files with 3563 additions and 133 deletions
Download patch file Download diff file Expand all files Collapse all files

16
examples/server/tests/unit/test_chat_completion.py
View file

@ -4,22 +4,26 @@ from utils import *
server = ServerPreset.tinyllama2()
@pytest.fixture(scope="module", autouse=True)
@pytest.fixture(autouse=True)
def create_server():
global server
server = ServerPreset.tinyllama2()
@pytest.mark.parametrize(
"model,system_prompt,user_prompt,max_tokens,re_content,n_prompt,n_predicted,finish_reason",
"model,system_prompt,user_prompt,max_tokens,re_content,n_prompt,n_predicted,finish_reason,jinja,chat_template",
[
(None, "Book", "What is the best book", 8, "(Suddenly)+", 77, 8, "length"),
("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length"),
(None, "Book", "What is the best book", 8, "(Suddenly)+", 77, 8, "length", False, None),
(None, "Book", "What is the best book", 8, "(Suddenly)+", 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"),
("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),
]
)
def test_chat_completion(model, system_prompt, user_prompt, max_tokens, re_content, n_prompt, n_predicted, finish_reason):
def test_chat_completion(model, system_prompt, user_prompt, max_tokens, re_content, n_prompt, n_predicted, finish_reason, jinja, chat_template):
global server
server.jinja = jinja
server.chat_template = chat_template
server.start()
res = server.make_request("POST", "/chat/completions", data={
"model": model,

7
examples/server/tests/utils.py
View file

@ -72,13 +72,14 @@ class ServerProcess:
pooling: str | None = None
draft: int | None = None
api_key: str | None = None
response_format: str | None = None
lora_files: List[str] | None = None
disable_ctx_shift: int | None = False
draft_min: int | None = None
draft_max: int | None = None
no_webui: bool | None = None
jinja: bool | None = None
chat_template: str | None = None
chat_template_file: str | None = None
# session variables
process: subprocess.Popen | None = None
@ -169,8 +170,12 @@ class ServerProcess:
server_args.extend(["--draft-min", self.draft_min])
if self.no_webui:
server_args.append("--no-webui")
if self.jinja:
server_args.append("--jinja")
if self.chat_template:
server_args.extend(["--chat-template", self.chat_template])
if self.chat_template_file:
server_args.extend(["--chat-template-file", self.chat_template_file])
args = [str(arg) for arg in [server_path, *server_args]]
print(f"bench: starting server with: {' '.join(args)}")