Enable Pydantic mypy checks and convert configs to Pydantic dataclasses (#17599)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -207,6 +207,9 @@ class LLM:
|
||||
if isinstance(worker_cls, type):
|
||||
kwargs["worker_cls"] = cloudpickle.dumps(worker_cls)
|
||||
|
||||
if hf_overrides is None:
|
||||
hf_overrides = {}
|
||||
|
||||
if compilation_config is not None:
|
||||
if isinstance(compilation_config, int):
|
||||
compilation_config_instance = CompilationConfig(
|
||||
@@ -218,7 +221,7 @@ class LLM:
|
||||
else:
|
||||
compilation_config_instance = compilation_config
|
||||
else:
|
||||
compilation_config_instance = None
|
||||
compilation_config_instance = CompilationConfig()
|
||||
|
||||
engine_args = EngineArgs(
|
||||
model=model,
|
||||
|
||||
@@ -175,11 +175,15 @@ class ChatCompletionNamedToolChoiceParam(OpenAIBaseModel):
|
||||
type: Literal["function"] = "function"
|
||||
|
||||
|
||||
# extra="forbid" is a workaround to have kwargs as a field,
|
||||
# see https://github.com/pydantic/pydantic/issues/3125
|
||||
class LogitsProcessorConstructor(BaseModel):
|
||||
qualname: str
|
||||
args: Optional[list[Any]] = None
|
||||
kwargs: Optional[dict[str, Any]] = None
|
||||
|
||||
model_config = ConfigDict(extra="forbid")
|
||||
|
||||
|
||||
LogitsProcessors = list[Union[str, LogitsProcessorConstructor]]
|
||||
|
||||
@@ -234,7 +238,7 @@ class ChatCompletionRequest(OpenAIBaseModel):
|
||||
presence_penalty: Optional[float] = 0.0
|
||||
response_format: Optional[AnyResponseFormat] = None
|
||||
seed: Optional[int] = Field(None, ge=_LONG_INFO.min, le=_LONG_INFO.max)
|
||||
stop: Optional[Union[str, list[str]]] = Field(default_factory=list)
|
||||
stop: Optional[Union[str, list[str]]] = []
|
||||
stream: Optional[bool] = False
|
||||
stream_options: Optional[StreamOptions] = None
|
||||
temperature: Optional[float] = None
|
||||
@@ -258,7 +262,7 @@ class ChatCompletionRequest(OpenAIBaseModel):
|
||||
min_p: Optional[float] = None
|
||||
repetition_penalty: Optional[float] = None
|
||||
length_penalty: float = 1.0
|
||||
stop_token_ids: Optional[list[int]] = Field(default_factory=list)
|
||||
stop_token_ids: Optional[list[int]] = []
|
||||
include_stop_str_in_output: bool = False
|
||||
ignore_eos: bool = False
|
||||
min_tokens: int = 0
|
||||
@@ -756,7 +760,7 @@ class CompletionRequest(OpenAIBaseModel):
|
||||
n: int = 1
|
||||
presence_penalty: Optional[float] = 0.0
|
||||
seed: Optional[int] = Field(None, ge=_LONG_INFO.min, le=_LONG_INFO.max)
|
||||
stop: Optional[Union[str, list[str]]] = Field(default_factory=list)
|
||||
stop: Optional[Union[str, list[str]]] = []
|
||||
stream: Optional[bool] = False
|
||||
stream_options: Optional[StreamOptions] = None
|
||||
suffix: Optional[str] = None
|
||||
@@ -770,7 +774,7 @@ class CompletionRequest(OpenAIBaseModel):
|
||||
min_p: Optional[float] = None
|
||||
repetition_penalty: Optional[float] = None
|
||||
length_penalty: float = 1.0
|
||||
stop_token_ids: Optional[list[int]] = Field(default_factory=list)
|
||||
stop_token_ids: Optional[list[int]] = []
|
||||
include_stop_str_in_output: bool = False
|
||||
ignore_eos: bool = False
|
||||
min_tokens: int = 0
|
||||
|
||||
@@ -134,11 +134,9 @@ class RequestProcessingMixin(BaseModel):
|
||||
Mixin for request processing,
|
||||
handling prompt preparation and engine input.
|
||||
"""
|
||||
request_prompts: Optional[Sequence[RequestPrompt]] = \
|
||||
Field(default_factory=list)
|
||||
request_prompts: Optional[Sequence[RequestPrompt]] = []
|
||||
engine_prompts: Optional[Union[list[EngineTokensPrompt],
|
||||
list[EngineEmbedsPrompt]]] = Field(
|
||||
default_factory=list)
|
||||
list[EngineEmbedsPrompt]]] = []
|
||||
|
||||
model_config = ConfigDict(arbitrary_types_allowed=True)
|
||||
|
||||
@@ -528,12 +526,14 @@ class OpenAIServing:
|
||||
if isinstance(request,
|
||||
(EmbeddingChatRequest, EmbeddingCompletionRequest,
|
||||
ScoreRequest, RerankRequest, ClassificationRequest)):
|
||||
operation = {
|
||||
ScoreRequest: "score",
|
||||
ClassificationRequest: "classification"
|
||||
}.get(type(request), "embedding generation")
|
||||
|
||||
if token_num > self.max_model_len:
|
||||
operations: dict[type[AnyRequest], str] = {
|
||||
ScoreRequest: "score",
|
||||
ClassificationRequest: "classification"
|
||||
}
|
||||
operation = operations.get(type(request),
|
||||
"embedding generation")
|
||||
raise ValueError(
|
||||
f"This model's maximum context length is "
|
||||
f"{self.max_model_len} tokens. However, you requested "
|
||||
|
||||
Reference in New Issue
Block a user