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

Update cancel.feature

Browse source
This commit is contained in:
ochafik 2024-09-29 19:37:23 +01:00
parent 231a5e4914
commit c5a0d57ee5
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/cancel.feature
View file

@ -18,10 +18,8 @@ Feature: Cancellation of llama.cpp server requests
And 64 server max tokens to predict And 64 server max tokens to predict
And prometheus compatible metrics exposed And prometheus compatible metrics exposed
And 300 milliseconds delay in sampler for testing And 300 milliseconds delay in sampler for testing
And no warmup
Then the server is starting Then the server is starting
Then the server is healthy Then the server is healthy
# Then the server is healthy with timeout 10 seconds
Scenario Outline: Cancelling an OAI chat completion request frees up slot (streaming <enable_streaming>) Scenario Outline: Cancelling an OAI chat completion request frees up slot (streaming <enable_streaming>)