[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
@@ -843,6 +843,15 @@ def w8a8_triton_block_scaled_mm(
assert len(block_size) == 2
block_n, block_k = block_size[0], block_size[1]
# Triton cannot currently bind E8M0 scale tensors directly. On ROCm,
# DeepSeek-V4 checkpoints store block scales in exponent-only E8M0 format,
# so decode them to fp32 before launching the kernel.
if current_platform.is_rocm():
if As.dtype == torch.float8_e8m0fnu:
As = _upcast_e8m0_to_fp32(As).contiguous()
if Bs.dtype == torch.float8_e8m0fnu:
Bs = _upcast_e8m0_to_fp32(Bs).contiguous()
assert A.shape[-1] == B.shape[-1]
assert A.shape[:-1] == As.shape[:-1] and A.is_contiguous()
assert triton.cdiv(A.shape[-1], block_k) == As.shape[-1]