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

server: tests: add a note regarding inference speed.

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-02-23 22:25:39 +01:00
parent 71831494b1
commit 2d107babc4
1 changed files with 9 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

10
examples/server/tests/README.md
View file

@ -1,6 +1,12 @@
# Server Integration Test
# Server tests
Server tests scenario using [BDD](https://en.wikipedia.org/wiki/Behavior-driven_development) with [behave](https://behave.readthedocs.io/en/latest/).
Python based server tests scenario using [BDD](https://en.wikipedia.org/wiki/Behavior-driven_development) and [behave](https://behave.readthedocs.io/en/latest/).
Tests target GitHub workflows job runners with 4 vCPU.
Requests are using [aiohttp](https://docs.aiohttp.org/en/stable/client_reference.html), [asyncio](https://docs.python.org/fr/3/library/asyncio.html) based http client.
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`