mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-11 21:39:52 +00:00
2002bc96bf
* server : refactoring (wip) * server : remove llava/clip objects from build * server : fix empty prompt handling + all slots idle logic * server : normalize id vars * server : code style * server : simplify model chat template validation * server : code style * server : minor * llama : llama_chat_apply_template support null buf * server : do not process embedding requests when disabled * server : reorganize structs and enums + naming fixes * server : merge oai.hpp in utils.hpp * server : refactor system prompt update at start * server : disable cached prompts with self-extend * server : do not process more than n_batch tokens per iter * server: tests: embeddings use a real embeddings model (#5908) * server, tests : bump batch to fit 1 embedding prompt * server: tests: embeddings fix build type Debug is randomly failing (#5911) * server: tests: embeddings, use different KV Cache size * server: tests: embeddings, fixed prompt do not exceed n_batch, increase embedding timeout, reduce number of concurrent embeddings * server: tests: embeddings, no need to wait for server idle as it can timout * server: refactor: clean up http code (#5912) * server : avoid n_available var ggml-ci * server: refactor: better http codes * server : simplify json parsing + add comment about t_last * server : rename server structs * server : allow to override FQDN in tests ggml-ci * server : add comments --------- Co-authored-by: Pierrick Hymbert <pierrick.hymbert@gmail.com>
101 lines
2.6 KiB
Gherkin
101 lines
2.6 KiB
Gherkin
@llama.cpp
|
|
@parallel
|
|
Feature: Parallel
|
|
|
|
Background: Server startup
|
|
Given a server listening on localhost:8080
|
|
And a model file tinyllamas/stories260K.gguf from HF repo ggml-org/models
|
|
And 42 as server seed
|
|
And 512 as batch size
|
|
And 64 KV cache size
|
|
And 2 slots
|
|
And continuous batching
|
|
Then the server is starting
|
|
Then the server is healthy
|
|
|
|
Scenario Outline: Multi users completion
|
|
Given a prompt:
|
|
"""
|
|
Write a very long story about AI.
|
|
"""
|
|
And a prompt:
|
|
"""
|
|
Write another very long music lyrics.
|
|
"""
|
|
And <n_predict> max tokens to predict
|
|
Given concurrent completion requests
|
|
Then the server is busy
|
|
Then the server is idle
|
|
And all slots are idle
|
|
Then all prompts are predicted with <n_predict> tokens
|
|
Examples:
|
|
| n_predict |
|
|
| 128 |
|
|
|
|
Scenario Outline: Multi users OAI completions compatibility
|
|
Given a system prompt You are a writer.
|
|
And a model tinyllama-2
|
|
Given a prompt:
|
|
"""
|
|
Write a very long book.
|
|
"""
|
|
And a prompt:
|
|
"""
|
|
Write another a poem.
|
|
"""
|
|
And <n_predict> max tokens to predict
|
|
And streaming is <streaming>
|
|
Given concurrent OAI completions requests
|
|
Then the server is busy
|
|
Then the server is idle
|
|
Then all prompts are predicted with <n_predict> tokens
|
|
Examples:
|
|
| streaming | n_predict |
|
|
| disabled | 128 |
|
|
| enabled | 64 |
|
|
|
|
Scenario Outline: Multi users OAI completions compatibility no v1
|
|
Given a system prompt You are a writer.
|
|
And a model tinyllama-2
|
|
Given a prompt:
|
|
"""
|
|
Write a very long book.
|
|
"""
|
|
And a prompt:
|
|
"""
|
|
Write another a poem.
|
|
"""
|
|
And <n_predict> max tokens to predict
|
|
And streaming is <streaming>
|
|
Given concurrent OAI completions requests no v1
|
|
Then the server is busy
|
|
Then the server is idle
|
|
Then all prompts are predicted with <n_predict> tokens
|
|
Examples:
|
|
| streaming | n_predict |
|
|
| disabled | 128 |
|
|
| enabled | 64 |
|
|
|
|
Scenario: Multi users with total number of tokens to predict exceeds the KV Cache size #3969
|
|
Given a prompt:
|
|
"""
|
|
Write a very long story about AI.
|
|
"""
|
|
And a prompt:
|
|
"""
|
|
Write another very long music lyrics.
|
|
"""
|
|
And a prompt:
|
|
"""
|
|
Write a very long poem.
|
|
"""
|
|
And a prompt:
|
|
"""
|
|
Write a very long joke.
|
|
"""
|
|
And 128 max tokens to predict
|
|
Given concurrent completion requests
|
|
Then the server is busy
|
|
Then the server is idle
|
|
Then all prompts are predicted
|