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

server: tests: simplify completion scenario

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-02-21 00:43:50 +01:00
parent 19664b9f01
commit 6dcbcfe6ba
1 changed files with 8 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

16
examples/server/tests/features/server.feature
View file

@ -14,12 +14,12 @@ Feature: llama.cpp server
@llama.cpp @llama.cpp
Scenario Outline: Completion Scenario Outline: Completion
Given a <prompt> completion request with maximum <n_predict> tokens Given a <prompt> completion request with maximum <n_predict> tokens
Then <predicted_n> tokens are predicted Then <n_predict> tokens are predicted
Examples: Prompts Examples: Prompts
| prompt | n_predict | predicted_n | | prompt | n_predict |
| I believe the meaning of life is | 128 | 128 | | I believe the meaning of life is | 128 |
| Write a joke about AI | 512 | 512 | | Write a joke about AI | 512 |
@llama.cpp @llama.cpp
Scenario Outline: OAI Compatibility Scenario Outline: OAI Compatibility
@ -29,12 +29,12 @@ Feature: llama.cpp server
And <max_tokens> max tokens to predict And <max_tokens> max tokens to predict
And streaming is <enable_streaming> And streaming is <enable_streaming>
Given an OAI compatible chat completions request Given an OAI compatible chat completions request
Then <predicted_n> tokens are predicted Then <max_tokens> tokens are predicted
Examples: Prompts Examples: Prompts
| model | system_prompt | user_prompt | max_tokens | enable_streaming | predicted_n | | model | system_prompt | user_prompt | max_tokens | enable_streaming |
| llama-2 | You are ChatGPT. | Say hello. | 64 | false | 64 | | llama-2 | You are ChatGPT. | Say hello. | 64 | false |
| codellama70b | You are a coding assistant. | Write the fibonacci function in c++. | 512 | true | 512 | | codellama70b | You are a coding assistant. | Write the fibonacci function in c++. | 512 | true |
@llama.cpp @llama.cpp
Scenario: Multi users Scenario: Multi users