mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
server : add support for external server for tests (#16243)
This commit adds support for using an externally started llama-server instance for the server tests. This can be enabled by setting the DEBUG_EXTERNAL environment variable. The motivation for this is to allow debugging of the server itself when investigating a test failure. Instructions for how to do this are added to the README.md file in the tests directory.
This commit is contained in:
@@ -64,3 +64,33 @@ cmake --build build -j --target llama-server && ./tools/server/tests/tests.sh
|
||||
```
|
||||
|
||||
To see all available arguments, please refer to [pytest documentation](https://docs.pytest.org/en/stable/how-to/usage.html)
|
||||
|
||||
### Debugging external llama-server
|
||||
It can sometimes be useful to run the server in a debugger when invesigating test
|
||||
failures. To do this, the environment variable `DEBUG_EXTERNAL=1` can be set
|
||||
which will cause the test to skip starting a llama-server itself. Instead, the
|
||||
server can be started in a debugger.
|
||||
|
||||
Example using `gdb`:
|
||||
```console
|
||||
$ gdb --args ../../../build/bin/llama-server \
|
||||
--host 127.0.0.1 --port 8080 \
|
||||
--temp 0.8 --seed 42 \
|
||||
--hf-repo ggml-org/models --hf-file tinyllamas/stories260K.gguf \
|
||||
--batch-size 32 --no-slots --alias tinyllama-2 --ctx-size 512 \
|
||||
--parallel 2 --n-predict 64
|
||||
```
|
||||
And a break point can be set in before running:
|
||||
```console
|
||||
(gdb) br server.cpp:4604
|
||||
(gdb) r
|
||||
main: server is listening on http://127.0.0.1:8080 - starting the main loop
|
||||
srv update_slots: all slots are idle
|
||||
```
|
||||
|
||||
And then the test in question can be run in another terminal:
|
||||
```console
|
||||
(venv) $ env DEBUG_EXTERNAL=1 ./tests.sh unit/test_chat_completion.py -v -x
|
||||
```
|
||||
And this should trigger the breakpoint and allow inspection of the server state
|
||||
in the debugger terminal.
|
||||
|
||||
@@ -99,8 +99,12 @@ class ServerProcess:
|
||||
self.debug = True
|
||||
if "PORT" in os.environ:
|
||||
self.server_port = int(os.environ["PORT"])
|
||||
self.external_server = "DEBUG_EXTERNAL" in os.environ
|
||||
|
||||
def start(self, timeout_seconds: int | None = DEFAULT_HTTP_TIMEOUT) -> None:
|
||||
if self.external_server:
|
||||
print(f"[external_server]: Assuming external server running on {self.server_host}:{self.server_port}")
|
||||
return
|
||||
if self.server_path is not None:
|
||||
server_path = self.server_path
|
||||
elif "LLAMA_SERVER_BIN_PATH" in os.environ:
|
||||
@@ -244,6 +248,9 @@ class ServerProcess:
|
||||
raise TimeoutError(f"Server did not start within {timeout_seconds} seconds")
|
||||
|
||||
def stop(self) -> None:
|
||||
if self.external_server:
|
||||
print("[external_server]: Not stopping external server")
|
||||
return
|
||||
if self in server_instances:
|
||||
server_instances.remove(self)
|
||||
if self.process:
|
||||
|
||||
Reference in New Issue
Block a user