[CPU][RISC-V] Add RVV micro GEMM for WNA16 (#44324)

Signed-off-by: wcy <233313160abc@gmail.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
wcy
2026-06-22 12:53:54 +00:00
committed by GitHub
co-authored by Li, Jiang <jiang1.li@intel.com>
parent b5a2adec4b
commit d2c671c29b
4 changed files with 273 additions and 2 deletions
@@ -9,7 +9,7 @@ from vllm.model_executor.layers.quantization.utils.quant_utils import (
pack_quantized_values_into_int32,
unpack_quantized_values_into_int32,
)
from vllm.platforms import current_platform
from vllm.platforms import CpuArchEnum, current_platform
from vllm.scalar_type import scalar_types
from .MPLinearKernel import MPLinearKernel, MPLinearLayerConfig
@@ -214,5 +214,7 @@ def _get_isa_hint(dtype: torch.dtype) -> str:
supports_amx = torch.cpu._is_amx_tile_supported()
if supports_amx and dtype in (torch.bfloat16,):
return "amx"
elif current_platform.get_cpu_architecture() == CpuArchEnum.RISCV:
return "rvv"
else:
return "vec"