Model: Change cache_size/max_seq_len behavior

- Cache size is now given only by the cache_size config option. Default is 4096 (user should always override to max out VRAM)
- max_seq_len, if not overridden in the config, will default to the model's config.json
- max_seq_len is reduced to be no larger than the cache

endpoints/core/types/model.py

@@ -85,7 +85,7 @@ class ModelLoadRequest(BaseModel):
         examples=[4096],
     )
     cache_size: Optional[int] = Field(
-        description=("Number in tokens, must be greater than or equal to max_seq_len"),
+        description="Number in tokens, must be multiple of 256",
         default=None,
         examples=[4096],
     )