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

server: tests: add truncated prompt tests, better kv cache size (#5933)

Browse source 
* server: tests: add truncated prompt tests, better size

* server, tests : update regex

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Pierrick Hymbert 2024-03-09 10:30:04 +01:00 • committed by GitHub
parent c2101a2e90
commit fd72d2d2a5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 81 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

35
examples/server/tests/features/steps/steps.py
View file

@ -196,12 +196,30 @@ async def step_request_completion(context, api_error):
@step(u'{predicted_n:d} tokens are predicted matching {re_content}')
def step_n_tokens_predicted_with_content(context, predicted_n, re_content):
assert_n_tokens_predicted(context.tasks_result.pop(), predicted_n, re_content)
context.completion = context.tasks_result.pop()
assert_n_tokens_predicted(context.completion, predicted_n, re_content)
@step(u'{predicted_n:d} tokens are predicted')
def step_n_tokens_predicted(context, predicted_n):
assert_n_tokens_predicted(context.tasks_result.pop(), predicted_n)
context.completion = context.tasks_result.pop()
assert_n_tokens_predicted(context.completion, predicted_n)
@step(u'the completion is truncated')
def step_assert_completion_truncated(context):
step_assert_completion_truncated(context, '')
@step(u'the completion is {truncated} truncated')
def step_assert_completion_truncated(context, truncated):
truncated = truncated != "not"
assert context.completion['truncated'] == truncated, f'{context.completion}'
@step(u'{n_prompt:d} prompt tokens are processed')
def step_impl(context, n_prompt):
assert n_prompt < 0 or n_prompt == context.completion['timings']['prompt_n'], f"n_prompt={context.completion['timings']['prompt_n']}"
@step(u'a user prompt {user_prompt}')
@ -722,7 +740,8 @@ async def oai_chat_completions(user_prompt,
completion_response = {
'content': '',
'timings': {
'predicted_n': 0
'predicted_n': 0,
'prompt_n': 0
}
}
if async_client:
@ -763,7 +782,8 @@ async def oai_chat_completions(user_prompt,
completion_response = {
'content': chat_completion_raw['choices'][0]['message'],
'timings': {
'predicted_n': chat_completion_raw['usage']['completion_tokens']
'predicted_n': chat_completion_raw['usage']['completion_tokens'],
'prompt_n': chat_completion_raw['usage']['prompt_tokens']
}
}
else:
@ -792,13 +812,16 @@ async def oai_chat_completions(user_prompt,
if 'content' in delta:
completion_response['content'] += delta['content']
completion_response['timings']['predicted_n'] += 1
completion_response['truncated'] = chunk.choices[0].finish_reason != 'stop'
else:
assert len(chat_completion.choices) == 1
completion_response = {
'content': chat_completion.choices[0].message.content,
'timings': {
'predicted_n': chat_completion.usage.completion_tokens
}
'predicted_n': chat_completion.usage.completion_tokens,
'prompt_n': chat_completion.usage.prompt_tokens
},
'truncated': chat_completion.choices[0].finish_reason != 'stop'
}
if debug:
print("OAI response formatted to llama.cpp:", completion_response)