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

server: init functional tests (#5566)

Browse source 
* server: tests: init scenarios
 - health and slots endpoints
 - completion endpoint
 - OAI compatible chat completion requests w/ and without streaming
 - completion multi users scenario
 - multi users scenario on OAI compatible endpoint with streaming
 - multi users with total number of tokens to predict exceeds the KV Cache size
 - server wrong usage scenario, like in Infinite loop of "context shift" #3969
 - slots shifting
 - continuous batching
 - embeddings endpoint
 - multi users embedding endpoint: Segmentation fault #5655
 - OpenAI-compatible embeddings API
 - tokenize endpoint
 - CORS and api key scenario

* server: CI GitHub workflow


---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Pierrick Hymbert 2024-02-24 12:28:55 +01:00 • committed by GitHub
parent fd43d66f46
commit 525213d2f5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 1243 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

21
examples/server/tests/features/wrong_usages.feature Normal file
View file

@ -0,0 +1,21 @@
# run with ./test.sh --tags wrong_usage
@wrong_usage
Feature: Wrong usage of llama.cpp server
#3969 The user must always set --n-predict option
# to cap the number of tokens any completion request can generate
# or pass n_predict/max_tokens in the request.
Scenario: Infinite loop
Given a server listening on localhost:8080
And a model file stories260K.gguf
# Uncomment below to fix the issue
#And 64 server max tokens to predict
Then the server is starting
Given a prompt:
"""
Go to: infinite loop
"""
# Uncomment below to fix the issue
#And 128 max tokens to predict
Given concurrent completion requests
Then all prompts are predicted