mirror of
https://github.com/deepseek-ai/FlashMLA
synced 2025-06-26 18:15:54 +00:00
16 lines
257 B
Python
16 lines
257 B
Python
"""FlashMLA: An efficient MLA decoding kernel for Hopper GPUs."""
|
|
|
|
from flash_mla.flash_mla_interface import (
|
|
get_mla_metadata,
|
|
flash_mla_with_kvcache,
|
|
)
|
|
|
|
|
|
__all__ = [
|
|
"get_mla_metadata",
|
|
"flash_mla_with_kvcache",
|
|
]
|
|
|
|
|
|
__version__ = "1.0.0"
|