API: Remove unncessary Optional signatures

Optional isn't necessary if the function signature has a default
value.

Signed-off-by: kingbri <bdashore3@proton.me>

endpoints/OAI/types/chat_completion.py

@@ -43,8 +43,8 @@ class ChatCompletionRequest(CommonCompletionRequest):
     # Take in a string as well even though it's not part of the OAI spec
     messages: Union[str, List[Dict[str, str]]]
     prompt_template: Optional[str] = None
-    add_generation_prompt: Optional[bool] = True
-    template_vars: Optional[dict] = {}
+    add_generation_prompt: bool = True
+    template_vars: dict = {}
     response_prefix: Optional[str] = None
 
 

endpoints/OAI/types/common.py

@@ -26,8 +26,8 @@ class CommonCompletionRequest(BaseSamplerRequest):
     model: Optional[str] = None
 
     # Generation info (remainder is in BaseSamplerRequest superclass)
-    stream: Optional[bool] = False
-    logprobs: Optional[int] = 0
+    stream: bool = False
+    logprobs: int = 0
     response_format: Optional[CompletionResponseFormat] = Field(
         default_factory=CompletionResponseFormat
     )
@@ -36,12 +36,10 @@ class CommonCompletionRequest(BaseSamplerRequest):
     best_of: Optional[int] = Field(
         description="Not parsed. Only used for OAI compliance.", default=None
     )
-    echo: Optional[bool] = Field(
+    echo: bool = Field(
         description="Not parsed. Only used for OAI compliance.", default=False
     )
-    n: Optional[int] = Field(
-        description="Not parsed. Only used for OAI compliance.", default=1
-    )
+    n: int = Field(description="Not parsed. Only used for OAI compliance.", default=1)
     suffix: Optional[str] = Field(
         description="Not parsed. Only used for OAI compliance.", default=None
     )

endpoints/OAI/types/lora.py

@@ -26,7 +26,7 @@ class LoraLoadInfo(BaseModel):
     """Represents a single Lora load info."""
 
     name: str
-    scaling: Optional[float] = 1.0
+    scaling: float = 1.0
 
 
 class LoraLoadRequest(BaseModel):

endpoints/OAI/types/model.py

@@ -13,10 +13,10 @@ class ModelCardParameters(BaseModel):
     # Safe to do this since it's guaranteed to fetch a max seq len
     # from model_container
     max_seq_len: Optional[int] = None
-    rope_scale: Optional[float] = 1.0
-    rope_alpha: Optional[float] = 1.0
-    cache_mode: Optional[str] = "FP16"
-    chunk_size: Optional[int] = 2048
+    rope_scale: float = 1.0
+    rope_alpha: float = 1.0
+    cache_mode: str = "FP16"
+    chunk_size: int = 2048
     prompt_template: Optional[str] = None
     num_experts_per_token: Optional[int] = None
     use_cfg: Optional[bool] = None
@@ -47,7 +47,7 @@ class DraftModelLoadRequest(BaseModel):
     """Represents a draft model load request."""
 
     draft_model_name: str
-    draft_rope_scale: Optional[float] = 1.0
+    draft_rope_scale: float = 1.0
     draft_rope_alpha: Optional[float] = Field(
         description="Automatically calculated if not present",
         default=None,
@@ -73,11 +73,9 @@ class ModelLoadRequest(BaseModel):
         default=None,
         examples=[4096],
     )
-    gpu_split_auto: Optional[bool] = True
-    autosplit_reserve: Optional[List[float]] = [96]
-    gpu_split: Optional[List[float]] = Field(
-        default_factory=list, examples=[[24.0, 20.0]]
-    )
+    gpu_split_auto: bool = True
+    autosplit_reserve: List[float] = [96]
+    gpu_split: List[float] = Field(default_factory=list, examples=[[24.0, 20.0]])
     rope_scale: Optional[float] = Field(
         description="Automatically pulled from the model's config if not present",
         default=None,
@@ -88,16 +86,16 @@ class ModelLoadRequest(BaseModel):
         default=None,
         examples=[1.0],
     )
-    no_flash_attention: Optional[bool] = False
+    no_flash_attention: bool = False
     # low_mem: Optional[bool] = False
-    cache_mode: Optional[str] = "FP16"
-    chunk_size: Optional[int] = 2048
+    cache_mode: str = "FP16"
+    chunk_size: int = 2048
     prompt_template: Optional[str] = None
     num_experts_per_token: Optional[int] = None
     use_cfg: Optional[bool] = None
-    fasttensors: Optional[bool] = False
+    fasttensors: bool = False
     draft: Optional[DraftModelLoadRequest] = None
-    skip_queue: Optional[bool] = False
+    skip_queue: bool = False
 
 
 class ModelLoadResponse(BaseModel):