mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-30 16:07:17 +01:00
6c5bc0625f
* server : (refactoring) reduce usage of json internally * move all response types to struct * wip [no ci] * many fixes * add virtual function * fix index * minor style fix * add std::move * refactor handle_completions_generic * add virtual functions * remove server.hpp * clarify server_sent_event RFC specs * apply review comments * fix model_alias and completion_probabilities * small clean up * remove virtual for to_json_oai_compat() * naming oai_compat --> oaicompat * fix unwanted recursive call * update docs
1.9 KiB
1.9 KiB
Server tests
Python based server tests scenario using pytest.
Tests target GitHub workflows job runners with 4 vCPU.
Note: If the host architecture inference speed is faster than GitHub runners one, parallel scenario may randomly fail.
To mitigate it, you can increase values in n_predict, kv_size.
Install dependencies
pip install -r requirements.txt
Run tests
- Build the server
cd ../../..
cmake -B build -DLLAMA_CURL=ON
cmake --build build --target llama-server
- Start the test:
./tests.sh
It's possible to override some scenario steps values with environment variables:
| variable | description |
|---|---|
PORT |
context.server_port to set the listening port of the server during scenario, default: 8080 |
LLAMA_SERVER_BIN_PATH |
to change the server binary path, default: ../../../build/bin/llama-server |
DEBUG |
to enable steps and server verbose mode --verbose |
N_GPU_LAYERS |
number of model layers to offload to VRAM -ngl --n-gpu-layers |
To run slow tests:
SLOW_TESTS=1 ./tests.sh
To run with stdout/stderr display in real time (verbose output, but useful for debugging):
DEBUG=1 ./tests.sh -s -v -x
Hint: You can compile and run test in single command, useful for local developement:
cmake --build build -j --target llama-server && ./examples/server/tests/tests.sh
To see all available arguments, please refer to pytest documentation