20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Misc] Remove unnecessary detokenization in multimodal processing (#12868)

Browse Source
This commit is contained in:
Cyrus Leung 2025-02-07 22:21:17 +08:00 committed by GitHub
parent 1918aa1b80
commit ce26b16268
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 7 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tests/entrypoints/openai/test_audio.py
View File

@ -83,7 +83,7 @@ async def test_single_chat_session_audio(client: openai.AsyncOpenAI,
choice = chat_completion.choices[0]
assert choice.finish_reason == "length"
assert chat_completion.usage == openai.types.CompletionUsage(
completion_tokens=10, prompt_tokens=202, total_tokens=212)
completion_tokens=10, prompt_tokens=201, total_tokens=211)
message = choice.message
message = chat_completion.choices[0].message
@ -140,7 +140,7 @@ async def test_single_chat_session_audio_base64encoded(
choice = chat_completion.choices[0]
assert choice.finish_reason == "length"
assert chat_completion.usage == openai.types.CompletionUsage(
completion_tokens=10, prompt_tokens=202, total_tokens=212)
completion_tokens=10, prompt_tokens=201, total_tokens=211)
message = choice.message
message = chat_completion.choices[0].message
@ -196,7 +196,7 @@ async def test_single_chat_session_input_audio(
choice = chat_completion.choices[0]
assert choice.finish_reason == "length"
assert chat_completion.usage == openai.types.CompletionUsage(
completion_tokens=10, prompt_tokens=202, total_tokens=212)
completion_tokens=10, prompt_tokens=201, total_tokens=211)
message = choice.message
message = chat_completion.choices[0].message

4
tests/entrypoints/openai/test_vision.py
View File

@ -92,7 +92,7 @@ async def test_single_chat_session_image(client: openai.AsyncOpenAI,
choice = chat_completion.choices[0]
assert choice.finish_reason == "length"
assert chat_completion.usage == openai.types.CompletionUsage(
completion_tokens=10, prompt_tokens=775, total_tokens=785)
completion_tokens=10, prompt_tokens=774, total_tokens=784)
message = choice.message
message = chat_completion.choices[0].message
@ -185,7 +185,7 @@ async def test_single_chat_session_image_base64encoded(
choice = chat_completion.choices[0]
assert choice.finish_reason == "length"
assert chat_completion.usage == openai.types.CompletionUsage(
completion_tokens=10, prompt_tokens=775, total_tokens=785)
completion_tokens=10, prompt_tokens=774, total_tokens=784)
message = choice.message
message = chat_completion.choices[0].message

4
tests/entrypoints/openai/test_vision_embedding.py
View File

@ -93,5 +93,5 @@ async def test_image_embedding(server: RemoteOpenAIServer, model_name: str,
assert len(embeddings.data) == 1
assert len(embeddings.data[0].embedding) == 3072
assert embeddings.usage.completion_tokens == 0
assert embeddings.usage.prompt_tokens == 764
assert embeddings.usage.total_tokens == 764
assert embeddings.usage.prompt_tokens == 763
assert embeddings.usage.total_tokens == 763

3
vllm/inputs/preprocess.py
View File

@ -260,9 +260,6 @@ class InputPreprocessor:
mm_processor = self.mm_registry.create_processor(
self.model_config, tokenizer)
if isinstance(prompt, list):
prompt = tokenizer.decode(prompt)
if mm_processor_kwargs is None:
mm_processor_kwargs = {}