mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-09-23 13:36:20 +00:00
bd60d82d0c
* server tests : remove seemingly redundant newlines in print() * server tests : use built-in subprocess features, not os.kill and psutil * server tests : do not catch e.g. SystemExit; use print_exc * server tests: handle TimeoutExpired exception * server tests: fix connect on dual-stack systems * server: tests: add new tokens regex on windows generated following new repeat penalties default changed in (#6127) * server: tests: remove the hack on windows since now we get the good socket family * server: tests: add new tokens regex following new repeat penalties default changed in (#6127) * server: tests: add new tokens regex following new repeat penalties default changed in (#6127) --------- Co-authored-by: Pierrick HYMBERT <pierrick.hymbert@gmail.com>
85 lines
3.8 KiB
Gherkin
85 lines
3.8 KiB
Gherkin
@llama.cpp
|
|
@server
|
|
Feature: llama.cpp server
|
|
|
|
Background: Server startup
|
|
Given a server listening on localhost:8080
|
|
And a model url https://huggingface.co/ggml-org/models/resolve/main/tinyllamas/stories260K.gguf
|
|
And a model file stories260K.gguf
|
|
And a model alias tinyllama-2
|
|
And 42 as server seed
|
|
# KV Cache corresponds to the total amount of tokens
|
|
# that can be stored across all independent sequences: #4130
|
|
# see --ctx-size and #5568
|
|
And 256 KV cache size
|
|
And 32 as batch size
|
|
And 2 slots
|
|
And 64 server max tokens to predict
|
|
And prometheus compatible metrics exposed
|
|
Then the server is starting
|
|
Then the server is healthy
|
|
|
|
Scenario: Health
|
|
Then the server is ready
|
|
And all slots are idle
|
|
|
|
|
|
Scenario Outline: Completion
|
|
Given a prompt <prompt>
|
|
And <n_predict> max tokens to predict
|
|
And a completion request with no api error
|
|
Then <n_predicted> tokens are predicted matching <re_content>
|
|
And the completion is <truncated> truncated
|
|
And <n_prompt> prompt tokens are processed
|
|
And prometheus metrics are exposed
|
|
And metric llamacpp:tokens_predicted is <n_predicted>
|
|
|
|
Examples: Prompts
|
|
| prompt | n_predict | re_content | n_prompt | n_predicted | truncated |
|
|
| I believe the meaning of life is | 8 | (read\|going)+ | 18 | 8 | not |
|
|
| Write a joke about AI from a very long prompt which will not be truncated | 256 | (princesses\|everyone\|kids\|Anna\|forest)+ | 46 | 64 | not |
|
|
|
|
Scenario: Completion prompt truncated
|
|
Given a prompt:
|
|
"""
|
|
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
|
|
Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.
|
|
Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
|
|
Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
|
|
"""
|
|
And a completion request with no api error
|
|
Then 64 tokens are predicted matching fun|Annaks|popcorns|pictry|bowl
|
|
And the completion is truncated
|
|
And 109 prompt tokens are processed
|
|
|
|
|
|
Scenario Outline: OAI Compatibility
|
|
Given a model <model>
|
|
And a system prompt <system_prompt>
|
|
And a user prompt <user_prompt>
|
|
And <max_tokens> max tokens to predict
|
|
And streaming is <enable_streaming>
|
|
Given an OAI compatible chat completions request with no api error
|
|
Then <n_predicted> tokens are predicted matching <re_content>
|
|
And <n_prompt> prompt tokens are processed
|
|
And the completion is <truncated> truncated
|
|
|
|
Examples: Prompts
|
|
| model | system_prompt | user_prompt | max_tokens | re_content | n_prompt | n_predicted | enable_streaming | truncated |
|
|
| llama-2 | Book | What is the best book | 8 | (Here\|what)+ | 77 | 8 | disabled | not |
|
|
| codellama70b | You are a coding assistant. | Write the fibonacci function in c++. | 128 | (thanks\|happy\|bird\|Annabyear)+ | -1 | 64 | enabled | |
|
|
|
|
|
|
Scenario: Tokenize / Detokenize
|
|
When tokenizing:
|
|
"""
|
|
What is the capital of France ?
|
|
"""
|
|
Then tokens can be detokenize
|
|
|
|
Scenario: Models available
|
|
Given available models
|
|
Then 1 models are supported
|
|
Then model 0 is identified by tinyllama-2
|
|
Then model 0 is trained on 128 tokens context
|