ViperEkura
32fd03a025
- CudaBackend: paged decode via attn_paged_decode, prefill via attn_prefill - Decode uses req_to_token as page_table with page_size=1 - Falls back to TorchNativeBackend when kernel unavailable - Rename forward_decode/forward_extend to fwd_decode/fwd_prefill - Register ATTN_BACKEND.CUDA in _BACKEND_REGISTRY
46 lines
1.3 KiB
Python
46 lines
1.3 KiB
Python
"""CUDA attention kernel wrappers with torch fallback.
|
|
|
|
Public API:
|
|
- ``attn_decode`` — single-query decode attention
|
|
- ``attn_prefill`` — multi-query prefill attention
|
|
- ``attn_paged_decode`` — paged decode attention (direct page-table access)
|
|
- ``AttentionBackend`` — ABC for attention computation strategies
|
|
- ``TorchNativeBackend`` — default SDPA backend with KV cache I/O
|
|
- ``CudaBackend`` — CUDA kernel backend with paged decode + prefill
|
|
|
|
Layout convention: all q/k/v are ``[batch, seq_len, n_heads, head_dim]``
|
|
(blhd). Scale is always ``1/sqrt(head_dim)``.
|
|
|
|
Each wrapper calls its compiled CUDA kernel directly. Fallback to torch
|
|
SDPA is handled by the attention backend, not the wrapper functions.
|
|
"""
|
|
|
|
from astrai.extension.attention_backend import (
|
|
ATTN_BACKEND,
|
|
AttentionBackend,
|
|
CudaBackend,
|
|
TorchNativeBackend,
|
|
attn_backend,
|
|
get_backend,
|
|
)
|
|
from astrai.extension.attention_ops import (
|
|
attn_decode,
|
|
attn_paged_decode,
|
|
attn_prefill,
|
|
)
|
|
from astrai.extension.loader import KERNEL_NAMES, is_available
|
|
|
|
__all__ = [
|
|
"ATTN_BACKEND",
|
|
"AttentionBackend",
|
|
"CudaBackend",
|
|
"TorchNativeBackend",
|
|
"attn_backend",
|
|
"get_backend",
|
|
"attn_decode",
|
|
"attn_paged_decode",
|
|
"attn_prefill",
|
|
"is_available",
|
|
"KERNEL_NAMES",
|
|
]
|