feat: add optional CUDA kernel system (csrc/) + fused GQA decode attention
Structure: csrc/ -- .cu sources + build.py registry astrai/extension/ -- compiled .so + __init__.py (import dispatcher) setup.py -- CUDAExtension from csrc/build.py REGISTRY Control: CSRC_KERNELS=true|false env var at install time. Fallback: astrai.extension.available dict for runtime detection.
This commit is contained in:
@@ -16,6 +16,7 @@ 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