biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Add full API docs and improve the UX of navigating them (#17485)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-05-04 03:42:43 +01:00
committed by GitHub
parent 46fae69cf0
commit d6484ef3c3
101 changed files with 872 additions and 980 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
vllm/inputs/preprocess.py
View File

@@ -224,7 +224,7 @@ class InputPreprocessor:
lora_request: Optional[LoRARequest],
tokenization_kwargs: Optional[dict[str, Any]] = None,
) -> list[int]:
"""Async version of :meth:`_tokenize_prompt`."""
"""Async version of {meth}`_tokenize_prompt`."""
tokenizer = self.get_tokenizer_group()
tokenization_kwargs = self._get_tokenization_kw(tokenization_kwargs)
@@ -287,7 +287,7 @@ class InputPreprocessor:
lora_request: Optional[LoRARequest],
return_mm_hashes: bool = False,
) -> MultiModalInputs:
"""Async version of :meth:`_process_multimodal`."""
"""Async version of {meth}`_process_multimodal`."""
tokenizer = await self._get_mm_tokenizer_async(lora_request)
mm_processor = self.mm_registry.create_processor(self.model_config,
@@ -472,7 +472,7 @@ class InputPreprocessor:
Returns:
* :class:`SingletonInputs` instance
* {class}`SingletonInputs` instance
"""
parsed = parse_singleton_prompt(prompt)
@@ -508,7 +508,7 @@ class InputPreprocessor:
lora_request: Optional[LoRARequest] = None,
return_mm_hashes: bool = False,
) -> SingletonInputs:
"""Async version of :meth:`_prompt_to_llm_inputs`."""
"""Async version of {meth}`_prompt_to_llm_inputs`."""
parsed = parse_singleton_prompt(prompt)
if parsed["type"] == "embeds":
@@ -644,7 +644,7 @@ class InputPreprocessor:
) -> EncoderDecoderInputs:
"""
For encoder/decoder models only:
Process an input prompt into an :class:`EncoderDecoderInputs` instance.
Process an input prompt into an {class}`EncoderDecoderInputs` instance.
There are two types of input prompts:
singleton prompts which carry only the
@@ -670,7 +670,7 @@ class InputPreprocessor:
Returns:
* :class:`EncoderDecoderInputs` instance
* {class}`EncoderDecoderInputs` instance
"""
encoder_inputs: SingletonInputs
decoder_inputs: Optional[SingletonInputs]
@@ -710,7 +710,7 @@ class InputPreprocessor:
prompt: PromptType,
tokenization_kwargs: Optional[dict[str, Any]] = None,
) -> EncoderDecoderInputs:
"""Async version of :meth:`_process_encoder_decoder_prompt`."""
"""Async version of {meth}`_process_encoder_decoder_prompt`."""
encoder_inputs: SingletonInputs
decoder_inputs: Optional[SingletonInputs]
@@ -778,7 +778,7 @@ class InputPreprocessor:
) -> DecoderOnlyInputs:
"""
For decoder-only models:
Process an input prompt into an :class:`DecoderOnlyInputs` instance.
Process an input prompt into an {class}`DecoderOnlyInputs` instance.
Arguments:
@@ -789,7 +789,7 @@ class InputPreprocessor:
Returns:
* :class:`DecoderOnlyInputs` instance
* {class}`DecoderOnlyInputs` instance
"""
prompt_comps = self._prompt_to_llm_inputs(
@@ -812,7 +812,7 @@ class InputPreprocessor:
prompt_adapter_request: Optional[PromptAdapterRequest] = None,
return_mm_hashes: bool = False,
) -> DecoderOnlyInputs:
"""Async version of :meth:`_process_decoder_only_prompt`."""
"""Async version of {meth}`_process_decoder_only_prompt`."""
prompt_comps = await self._prompt_to_llm_inputs_async(
prompt,
tokenization_kwargs=tokenization_kwargs,
@@ -863,7 +863,7 @@ class InputPreprocessor:
prompt_adapter_request: Optional[PromptAdapterRequest] = None,
return_mm_hashes: bool = False,
) -> ProcessorInputs:
"""Async version of :meth:`preprocess`."""
"""Async version of {meth}`preprocess`."""
if self.model_config.is_encoder_decoder:
assert not return_mm_hashes, (
"Multimodal hashes for encoder-decoder models should not be ",