Revision to paged attention checks (#133)

* Model: Clean up paged attention checks

* Model: Move cache_size checks after paged attn checks
Cache size is only relevant in paged mode

* Model: Fix no_flash_attention

* Model: Remove no_flash_attention
Ability to use flash attention is auto-detected, so this flag is unneeded. Uninstall flash attention to disable it on supported hardware.

endpoints/OAI/types/model.py

@@ -94,7 +94,6 @@ class ModelLoadRequest(BaseModel):
         default=None,
         examples=[1.0],
     )
-    no_flash_attention: Optional[bool] = False
     # low_mem: Optional[bool] = False
     cache_mode: Optional[str] = "FP16"
     chunk_size: Optional[int] = 2048