refactor: extension dispatch layer with CUDA/torch fallback
- Add gqa_decode_attn/gqa_prefill_attn dispatch functions - Internal _available/__modules with underscore prefix - CUDA kernel path with F.scaled_dot_product_attention fallback - GQA head expansion in fallback path
This commit is contained in:
@@ -16,7 +16,6 @@ from astrai.dataset import (
|
||||
Store,
|
||||
StoreFactory,
|
||||
)
|
||||
from astrai.extension import available
|
||||
from astrai.factory import BaseFactory
|
||||
from astrai.inference import (
|
||||
GenerationRequest,
|
||||
|
||||
Reference in New Issue
Block a user