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

server: tests: embeddings, no need to wait for server idle as it can timout

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-03-06 21:59:31 +01:00
parent 59850f18e5
commit 3166ccf5aa
1 changed files with 0 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server/tests/features/embeddings.feature
View file

@ -91,6 +91,4 @@ Feature: llama.cpp server
Given 10 fixed prompts Given 10 fixed prompts
And a model bert-bge-small And a model bert-bge-small
Given concurrent OAI embedding requests Given concurrent OAI embedding requests
Then the server is busy
Then the server is idle
Then all embeddings are the same Then all embeddings are the same