ViperEkura
3067a8e1a6
- Add attention() functional entry delegating to active backend - GQA/MLA forward calls attention() instead of inline cache/SDPA - CUDA kernels support 2D/3D/4D mask via mask_h_stride field - CudaBackend.fwd_decode builds 2D padding mask for mixed seq_lens - KVCache.max_len precomputed in bind_tasks to avoid GPU sync - batch==1 decode short-circuits mask=None - Split tests into conftest, test_backend, test_backend_equivalence, test_kernel_mask - 440 tests pass, L20 decode 1.44-1.60x speedup vs torch native
48 lines
1.3 KiB
Python
48 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,
|
|
attention,
|
|
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",
|
|
"attention",
|
|
"attn_backend",
|
|
"get_backend",
|
|
"attn_decode",
|
|
"attn_paged_decode",
|
|
"attn_prefill",
|
|
"is_available",
|
|
"KERNEL_NAMES",
|
|
]
|