OAI: Add API-based model loading/unloading and auth routes

Models can be loaded and unloaded via the API. Also add authentication
to use the API and for administrator tasks.

Both types of authorization use different keys.

Also fix the unload function to properly free all used vram.

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

OAI/types/common.py

@@ -0,0 +1,13 @@
+from pydantic import BaseModel, Field
+from typing import List, Dict
+
+class LogProbs(BaseModel):
+    text_offset: List[int] = Field(default_factory=list)
+    token_logprobs: List[float] = Field(default_factory=list)
+    tokens: List[str] = Field(default_factory=list)
+    top_logprobs: List[Dict[str, float]] = Field(default_factory=list)
+
+class UsageStats(BaseModel):
+    completion_tokens: int
+    prompt_tokens: int
+    total_tokens: int