[New Model][ROCm] Add AMD support for DeepSeek V4 (#40871)

Signed-off-by: ganyi <ygan@amd.com>
Signed-off-by: whx-sjtu <xiaowang990929@gmail.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: tjtanaavllm <tunjian.tan@amd.com>
Co-authored-by: ganyi <ygan@amd.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaavllm <tunjian.tan@amd.com>
This commit is contained in:
Hexiang Wang
2026-05-05 08:55:37 -07:00
committed by GitHub
co-authored by ganyi tjtanaa tjtanaavllm
parent 2228fe6868
commit 628c436301
22 changed files with 939 additions and 134 deletions
@@ -312,6 +312,21 @@ class AiterFp8BlockScaledMMKernel(Fp8BlockScaledMMLinearKernel):
As: torch.Tensor,
Bs: torch.Tensor,
) -> torch.Tensor:
if As.dtype != Bs.dtype:
from vllm.model_executor.layers.quantization.utils.fp8_utils import (
_upcast_e8m0_to_fp32,
)
if As.dtype == torch.float8_e8m0fnu:
As = _upcast_e8m0_to_fp32(As).contiguous()
else:
As = As.to(torch.float32)
if Bs.dtype == torch.float8_e8m0fnu:
Bs = _upcast_e8m0_to_fp32(Bs).contiguous()
else:
Bs = Bs.to(torch.float32)
out_dtype = self.config.out_dtype
if self.use_triton:
gemm_a8w8_blockscale_op = rocm_aiter_ops.triton_gemm_a8w8_blockscale