[CPU][RISC-V] Add RVV-optimized attention kernels for RISC-V Vector Extension (#40119)

Signed-off-by: liuyudong <liuyudong@iscas.ac.cn>
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
lyd1992
2026-05-15 12:08:23 +08:00
committed by GitHub
co-authored by Claude
parent 56434e8651
commit f351455f0f
11 changed files with 624 additions and 33 deletions
+9 -11
View File
@@ -12,7 +12,6 @@ from vllm._custom_ops import (
cpu_attn_get_scheduler_metadata,
cpu_attn_reshape_and_cache,
)
from vllm.platforms import CpuArchEnum, current_platform
from vllm.utils.argparse_utils import FlexibleArgumentParser
from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE, set_random_seed
from vllm.v1.attention.backends.cpu_attn import CPUAttentionBackend, _get_attn_isa
@@ -22,15 +21,14 @@ def get_attn_isa(
block_size: int | None = None,
dtype: torch.dtype | None = None,
):
if block_size and dtype:
return _get_attn_isa(dtype, block_size)
else:
if current_platform.get_cpu_architecture() == CpuArchEnum.ARM:
return "neon"
elif torch.cpu._is_amx_tile_supported():
return "amx"
else:
return "vec"
# Delegate to _get_attn_isa so the fallback path applies the same arch
# gating (e.g. RISC-V RVV is only chosen when the build's hardcoded
# VLEN=128 kernel is actually present; on VLEN=256 / scalar hosts it
# correctly falls through to vec/vec16).
return _get_attn_isa(
dtype if dtype is not None else torch.bfloat16,
block_size if block_size else 32,
)
# rand number generation takes too much time, cache rand tensors
@@ -235,7 +233,7 @@ if __name__ == "__main__":
)
parser.add_argument("--use-sink", action="store_true")
parser.add_argument(
"--isa", type=str, choices=["vec", "neon", "amx", "vec16"], default=None
"--isa", type=str, choices=["vec", "neon", "amx", "vec16", "rvv"], default=None
)
parser.add_argument("--seed", type=int, default=0)
parser.add_argument("--iters", type=int, default=20)