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

Update tests readme + add raw output to verbose log

Browse source
This commit is contained in:
ochafik 2025-01-30 00:43:30 +00:00
parent 774557cfb4
commit 590c97931a
2 changed files with 11 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/server/server.cpp
View file

@ -2302,6 +2302,7 @@ struct server_context {
res->oaicompat_model = slot.params.oaicompat_model;
res->oaicompat_cmpl_id = slot.params.oaicompat_cmpl_id;
if (slot.params.chat_parser) {
LOG_DBG("Raw chat output: %s\n", slot.generated_text.c_str());
res->message = slot.params.chat_parser(slot.generated_text);
} else {
res->message = {

13
examples/server/tests/README.md
View file

@ -31,8 +31,9 @@ It's possible to override some scenario steps values with environment variables:
| `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` |
| `LLAMA_CACHE` | by default server tests re-download models to the `tmp` subfolder. Set this to your cache (e.g. `$HOME/Library/Caches/llama.cpp` on Mac or `$HOME/.cache/llama.cpp` on Unix) to avoid this |
To run slow tests:
To run slow tests (will download many models, make sure to set `LLAMA_CACHE` if needed):
```shell
SLOW_TESTS=1 ./tests.sh
@ -44,10 +45,16 @@ To run with stdout/stderr display in real time (verbose output, but useful for d
DEBUG=1 ./tests.sh -s -v -x
```
To run single test unit:
To run all the tests in a file:
```shell
./tests.sh unit/test_{name of test case here}.py -v -x
./tests.sh unit/test_chat_completion.py.py -v -x
```
To run a single test:
```shell
./tests.sh unit/test_chat_completion.py::test_invalid_chat_completion_req
```
Hint: You can compile and run test in single command, useful for local developement: