In-Tree AMD Zen CPU Backend via zentorch [1/N] (#35970)

Signed-off-by: Lalithnarayan C <Lalithnarayan.C@amd.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Chinmay-Kulkarni-AMD <Chinmay.Kulkarni@amd.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Lalithnarayan C
2026-03-15 23:35:35 +00:00
committed by GitHub
co-authored by Chinmay-Kulkarni-AMD Tyler Michael Smith Tyler Michael Smith Claude Sonnet 4.6
parent 697e4ff352
commit 7acaea634c
9 changed files with 261 additions and 2 deletions
+24
View File
@@ -231,6 +231,30 @@ def dispatch_cpu_unquantized_gemm(
N, K = layer.weight.size()
dtype = layer.weight.dtype
# Zen CPU path: zentorch_linear_unary with optional eager weight prepacking.
if current_platform.is_zen_cpu() and hasattr(
torch.ops.zentorch, "zentorch_linear_unary"
):
zen_weight = layer.weight.detach()
is_prepacked = False
if envs.VLLM_ZENTORCH_WEIGHT_PREPACK and hasattr(
torch.ops.zentorch, "zentorch_weight_prepack_for_linear"
):
zen_weight = torch.ops.zentorch.zentorch_weight_prepack_for_linear(
zen_weight
)
is_prepacked = True
layer.cpu_linear = lambda x, weight, bias, _p=is_prepacked: (
torch.ops.zentorch.zentorch_linear_unary(
x, zen_weight, bias, is_weight_prepacked=_p
)
)
if remove_weight:
layer.weight = torch.nn.Parameter(torch.empty(0), requires_grad=False)
return
if envs.VLLM_CPU_SGL_KERNEL and check_cpu_sgl_kernel(N, K, dtype):
packed_weight = torch.ops._C.convert_weight_packed(layer.weight)
if getattr(layer, "bias", None) is not None: