[ZenCPU] Add zencpu Platform Runtime Logging and Docs (#42726)
Signed-off-by: Lalithnarayan C <Lalithnarayan.C@amd.com> Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com> Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
co-authored by
Tyler Michael Smith
Claude
Tyler Michael Smith
parent
3f53e2138f
commit
405c7cf283
@@ -272,6 +272,10 @@ def dispatch_cpu_unquantized_gemm(
|
||||
)
|
||||
if remove_weight:
|
||||
layer.weight = torch.nn.Parameter(torch.empty(0), requires_grad=False)
|
||||
logger.debug_once(
|
||||
"CPU unquantized GEMM dispatch: using zentorch_linear_unary (prepacked=%s)",
|
||||
is_prepacked,
|
||||
)
|
||||
return
|
||||
|
||||
if envs.VLLM_CPU_SGL_KERNEL and check_cpu_sgl_kernel(N, K, dtype):
|
||||
@@ -285,6 +289,9 @@ def dispatch_cpu_unquantized_gemm(
|
||||
)
|
||||
if remove_weight:
|
||||
layer.weight = torch.nn.Parameter(torch.empty(0), requires_grad=False)
|
||||
logger.debug_once(
|
||||
"CPU unquantized GEMM dispatch: using sgl-kernel weight_packed_linear"
|
||||
)
|
||||
return
|
||||
elif (
|
||||
ops._supports_onednn
|
||||
@@ -296,6 +303,7 @@ def dispatch_cpu_unquantized_gemm(
|
||||
layer.cpu_linear = lambda x, weight, bias: ops.onednn_mm(handler, x, bias)
|
||||
if remove_weight:
|
||||
layer.weight = torch.nn.Parameter(torch.empty(0), requires_grad=False)
|
||||
logger.debug_once("CPU unquantized GEMM dispatch: using oneDNN onednn_mm")
|
||||
return
|
||||
except RuntimeError as e:
|
||||
logger.warning_once(
|
||||
@@ -307,6 +315,9 @@ def dispatch_cpu_unquantized_gemm(
|
||||
layer.cpu_linear = lambda x, weight, bias: torch.nn.functional.linear(
|
||||
x, weight, bias
|
||||
)
|
||||
logger.debug_once(
|
||||
"CPU unquantized GEMM dispatch: using torch.nn.functional.linear (fallback)"
|
||||
)
|
||||
|
||||
|
||||
def cpu_unquantized_gemm(
|
||||
|
||||
Reference in New Issue
Block a user