[Docs] optimize and supplement docs system (#86)

Signed-off-by: Gaohan123 <gaohan19@huawei.com>
This commit is contained in:
Gao Han authored and GitHub committed 2025-11-28 11:03:52 +08:00
1 parent 38f58064eb
commit db81ee9f69
75 files changed
+2452 -512

No files matched your search

+50 -1
View File
@@ -11,6 +11,17 @@ from vllm.inputs.data import EmbedsPrompt, TokenInputs, TokensPrompt
class OmniTokensPrompt(TokensPrompt):
"""Tokens prompt with optional embeddings and additional information.
Extends TokensPrompt to support prompt embeddings and additional
information payloads for direct transfer between pipeline stages.
Attributes:
prompt_embeds: Optional tensor containing prompt embeddings
additional_information: Optional dictionary containing additional
information (tensors or lists) to pass along with the prompt
"""
prompt_embeds: NotRequired[torch.Tensor]
"""The embeddings of the prompt."""
@@ -20,6 +31,18 @@ class OmniTokensPrompt(TokensPrompt):
class OmniTokenInputs(TokenInputs):
"""Token inputs with optional embeddings and additional information.
Extends TokenInputs to support prompt embeddings and additional
information payloads for direct transfer between pipeline stages.
Attributes:
prompt_embeds: Optional tensor containing prompt embeddings
aligned with token IDs
additional_information: Optional dictionary containing additional
information (tensors or lists) to pass along with the inputs
"""
# New: optional prompt embeddings aligned with token ids
prompt_embeds: NotRequired[torch.Tensor]
@@ -29,6 +52,17 @@ class OmniTokenInputs(TokenInputs):
class OmniEmbedsPrompt(EmbedsPrompt):
"""Embeddings prompt with optional additional information.
Extends EmbedsPrompt to support additional information payloads
for direct transfer between pipeline stages.
Attributes:
prompt_embeds: Optional tensor containing prompt embeddings
additional_information: Optional dictionary containing additional
information (tensors or lists) to pass along with the prompt
"""
# New: optional prompt embeddings aligned with token ids
prompt_embeds: NotRequired[torch.Tensor]
@@ -44,7 +78,22 @@ def token_inputs_omni(
prompt_embeds: Optional[torch.Tensor] = None,
additional_information: Optional[dict[str, Any]] = None,
) -> OmniTokenInputs:
"""Construct token inputs with optional embeddings and metadata."""
"""Construct token inputs with optional embeddings and metadata.
Creates an OmniTokenInputs object with token IDs and optional
embeddings and additional information for pipeline stage transfer.
Args:
prompt_token_ids: List of token IDs for the prompt
prompt: Optional prompt string
cache_salt: Optional cache salt for prefix caching
prompt_embeds: Optional tensor containing prompt embeddings
additional_information: Optional dictionary containing additional
information (tensors or lists)
Returns:
OmniTokenInputs instance with the provided data
"""
inputs = OmniTokenInputs(type="token", prompt_token_ids=prompt_token_ids)
if prompt is not None:
+17
View File
@@ -9,6 +9,23 @@ from vllm.inputs.parse import (
def parse_singleton_prompt_omni(prompt: SingletonPrompt) -> ParsedSingletonPrompt:
"""Parse a singleton prompt into a typed parsed prompt.
Handles omni-specific prompt types including tokens prompts with
embeddings and additional information. Supports string, text,
tokens, and embeddings prompts.
Args:
prompt: Singleton prompt to parse. Can be a string, TextPrompt,
TokensPrompt (with optional prompt_embeds and additional_information),
or EmbedsPrompt.
Returns:
ParsedSingletonPrompt containing the parsed prompt with type information
Raises:
TypeError: If the prompt type is not supported
"""
if isinstance(prompt, str):
return ParsedStrPrompt(type="str", content=prompt)
elif isinstance(prompt, dict):
+7
View File
@@ -13,6 +13,13 @@ logger = init_logger(__name__)
class OmniInputPreprocessor(InputPreprocessor):
"""Input preprocessor for omni models.
Extends the base InputPreprocessor to handle omni-specific input
types including prompt embeddings and additional information payloads.
Supports processing tokens, embeddings, text, and multimodal inputs.
"""
def _process_tokens(
self,
parsed_content: TokensPrompt,