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 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	common/CMakeLists.txt
#	docs/backend/SYCL.md
#	docs/build.md
#	docs/docker.md
#	examples/export-lora/export-lora.cpp
#	examples/main/README.md
#	examples/main/main.cpp
#	examples/run/README.md
#	examples/run/run.cpp
#	examples/server/README.md
#	examples/simple-chat/simple-chat.cpp
#	ggml/CMakeLists.txt
#	ggml/src/ggml-hip/CMakeLists.txt
#	src/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
This commit is contained in:
Concedo 2025-01-25 14:16:50 +08:00
commit bec231422a
46 changed files with 4305 additions and 578 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)}")