huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-26 12:32:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Upgrade other tests.

Browse Source
This commit is contained in:
Nicolas Patry 2025-03-06 16:19:37 +01:00
parent ad904be5fc
commit 0e0844ce00
No known key found for this signature in database
GPG Key ID: 4242CEF24CB6DBF9
4 changed files with 48 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
integration-tests/conftest.py
View File

@ -42,6 +42,7 @@ from syrupy.extensions.json import JSONSnapshotExtension
from text_generation import AsyncClient
from text_generation.types import (
Completion,
BestOfSequence,
Message,
ChatComplete,
@ -131,6 +132,7 @@ class ResponseComparator(JSONSnapshotExtension):
or isinstance(data, ChatComplete)
or isinstance(data, ChatCompletionChunk)
or isinstance(data, ChatCompletionComplete)
or isinstance(data, Completion)
or isinstance(data, OAIChatCompletionChunk)
):
data = data.model_dump()
@ -140,6 +142,8 @@ class ResponseComparator(JSONSnapshotExtension):
data = dict(data)
elif isinstance(data, List):
data = [self._serialize(d) for d in data]
elif isinstance(data, dict):
return data
else:
raise RuntimeError(f"Unexpected data {type(data)} : {data}")
return data

69
integration-tests/models/__snapshots__/test_completion_prompts/test_flash_llama_completion_stream_usage.json
View File

@ -12,11 +12,11 @@
"logprobs": null
}
],
"created": 1726656043,
"created": 1741274364,
"id": "",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"object": "chat.completion.chunk",
"system_fingerprint": "2.2.1-dev0-native",
"system_fingerprint": "3.1.2-dev0-native",
"usage": null
},
{
@ -32,11 +32,11 @@
"logprobs": null
}
],
"created": 1726656043,
"created": 1741274364,
"id": "",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"object": "chat.completion.chunk",
"system_fingerprint": "2.2.1-dev0-native",
"system_fingerprint": "3.1.2-dev0-native",
"usage": null
},
{
@ -52,11 +52,11 @@
"logprobs": null
}
],
"created": 1726656043,
"created": 1741274364,
"id": "",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"object": "chat.completion.chunk",
"system_fingerprint": "2.2.1-dev0-native",
"system_fingerprint": "3.1.2-dev0-native",
"usage": null
},
{
@ -72,11 +72,11 @@
"logprobs": null
}
],
"created": 1726656043,
"created": 1741274364,
"id": "",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"object": "chat.completion.chunk",
"system_fingerprint": "2.2.1-dev0-native",
"system_fingerprint": "3.1.2-dev0-native",
"usage": null
},
{
@ -92,11 +92,11 @@
"logprobs": null
}
],
"created": 1726656043,
"created": 1741274364,
"id": "",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"object": "chat.completion.chunk",
"system_fingerprint": "2.2.1-dev0-native",
"system_fingerprint": "3.1.2-dev0-native",
"usage": null
},
{
@ -112,11 +112,11 @@
"logprobs": null
}
],
"created": 1726656043,
"created": 1741274364,
"id": "",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"object": "chat.completion.chunk",
"system_fingerprint": "2.2.1-dev0-native",
"system_fingerprint": "3.1.2-dev0-native",
"usage": null
},
{
@ -132,11 +132,11 @@
"logprobs": null
}
],
"created": 1726656044,
"created": 1741274364,
"id": "",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"object": "chat.completion.chunk",
"system_fingerprint": "2.2.1-dev0-native",
"system_fingerprint": "3.1.2-dev0-native",
"usage": null
},
{
@ -152,11 +152,11 @@
"logprobs": null
}
],
"created": 1726656044,
"created": 1741274364,
"id": "",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"object": "chat.completion.chunk",
"system_fingerprint": "2.2.1-dev0-native",
"system_fingerprint": "3.1.2-dev0-native",
"usage": null
},
{
@ -172,11 +172,11 @@
"logprobs": null
}
],
"created": 1726656044,
"created": 1741274364,
"id": "",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"object": "chat.completion.chunk",
"system_fingerprint": "2.2.1-dev0-native",
"system_fingerprint": "3.1.2-dev0-native",
"usage": null
},
{
@ -192,11 +192,20 @@
"logprobs": null
}
],
"created": 1726656044,
"created": 1741274364,
"id": "",
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"object": "chat.completion.chunk",
"system_fingerprint": "2.2.1-dev0-native",
"system_fingerprint": "3.1.2-dev0-native",
"usage": null
},
{
"choices": [],
"created": 1741274364,
"id": "",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"object": "chat.completion.chunk",
"system_fingerprint": "3.1.2-dev0-native",
"usage": {
"completion_tokens": 10,
"prompt_tokens": 40,

6
integration-tests/models/test_completion_prompts.py
View File

@ -96,8 +96,10 @@ async def test_flash_llama_completion_stream_usage(
assert not had_usage
if has_usage:
had_usage = True
elif c["usage"]:
had_usage = True
else:
raise RuntimeError("Expected different payload")
raise RuntimeError(f"Expected different payload: {c}")
assert had_usage
assert (
string
@ -147,6 +149,8 @@ async def test_flash_llama_completion_stream_usage(
assert not had_usage
if has_usage:
had_usage = True
elif c["usage"]:
had_usage = True
else:
raise RuntimeError("Expected different payload")
assert not had_usage

2
integration-tests/models/test_tools_llama.py
View File

@ -1,6 +1,4 @@
import pytest
import requests
import json
from openai import OpenAI
from huggingface_hub import InferenceClient
from huggingface_hub.inference._generated.types.chat_completion import (