[Render] Add round trip parity test and docs for derender (#48617)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
This commit is contained in:
@@ -266,8 +266,13 @@ class DerenderChatRequest(BaseModel):
|
||||
and ``parser.parse_delta()`` instead of ``parser.parse()``.
|
||||
"""
|
||||
|
||||
# --8<-- [start:derender-chat-request]
|
||||
model: str
|
||||
"""Served model name."""
|
||||
|
||||
generate_response: GenerateResponse
|
||||
"""The complete token-in / token-out engine response to derender."""
|
||||
|
||||
prompt_tokens: int | None = None
|
||||
"""Prompt token count for usage; defaults to 0 if omitted.
|
||||
|
||||
@@ -282,6 +287,7 @@ class DerenderChatRequest(BaseModel):
|
||||
request context they expect (request.tools, request.tool_choice,
|
||||
request._grammar_from_tool_parser, etc.).
|
||||
"""
|
||||
# --8<-- [end:derender-chat-request]
|
||||
|
||||
|
||||
class DerenderCompletionRequest(BaseModel):
|
||||
@@ -292,8 +298,14 @@ class DerenderCompletionRequest(BaseModel):
|
||||
returned by /v1/completions/render.
|
||||
"""
|
||||
|
||||
# --8<-- [start:derender-completion-request]
|
||||
model: str
|
||||
"""Served model name."""
|
||||
|
||||
generate_responses: list[GenerateResponse]
|
||||
"""One response per prompt, parallel to the list[GenerateRequest]
|
||||
returned by /v1/completions/render."""
|
||||
|
||||
prompt_tokens: list[int] | None = None
|
||||
"""One prompt token count per response; each defaults to 0 if omitted.
|
||||
|
||||
@@ -306,6 +318,7 @@ class DerenderCompletionRequest(BaseModel):
|
||||
Mirrors chat_request on DerenderChatRequest. Required by the parsing
|
||||
so parsers receive the full request context.
|
||||
"""
|
||||
# --8<-- [end:derender-completion-request]
|
||||
|
||||
@model_validator(mode="after")
|
||||
def _validate_prompt_tokens_length(self) -> "DerenderCompletionRequest":
|
||||
|
||||
@@ -7,6 +7,7 @@ from vllm.entrypoints.chat_utils import ChatTemplateContentFormatOption
|
||||
from vllm.entrypoints.generate.base.serving import resolve_token_id_placeholder
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionLogProbs,
|
||||
ChatCompletionNamedToolChoiceParam,
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionResponseChoice,
|
||||
ChatMessage,
|
||||
@@ -136,6 +137,13 @@ class OnlineDerenderer:
|
||||
else []
|
||||
)
|
||||
|
||||
is_named_tool_choice = (
|
||||
type(chat_request.tool_choice) is ChatCompletionNamedToolChoiceParam
|
||||
)
|
||||
is_required_tool_choice = chat_request.tool_choice == "required"
|
||||
if is_named_tool_choice or is_required_tool_choice:
|
||||
content = content or ""
|
||||
|
||||
message = ChatMessage(
|
||||
role="assistant",
|
||||
reasoning=reasoning,
|
||||
|
||||
Reference in New Issue
Block a user