[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:
Lalithnarayan C
2026-06-16 08:23:12 -04:00
committed by GitHub
co-authored by Tyler Michael Smith Claude Tyler Michael Smith
parent 3f53e2138f
commit 405c7cf283
6 changed files with 108 additions and 3 deletions
@@ -66,3 +66,26 @@ def test_dispatch_cpu_unquantized_gemm_zen_remove_weight(monkeypatch):
utils.dispatch_cpu_unquantized_gemm(layer, remove_weight=True)
assert layer.weight.numel() == 0
@pytest.mark.usefixtures("_mock_zentorch_linear_unary")
def test_dispatch_cpu_unquantized_gemm_logs_zentorch_dispatch(monkeypatch):
monkeypatch.setattr(current_platform, "is_zen_cpu", lambda: True)
expected_prepacked = bool(utils.envs.VLLM_ZENTORCH_WEIGHT_PREPACK) and hasattr(
torch.ops.zentorch, "zentorch_weight_prepack_for_linear"
)
log_calls = []
monkeypatch.setattr(
utils.logger, "debug_once", lambda *args: log_calls.append(args)
)
layer = torch.nn.Linear(16, 8, bias=True)
utils.dispatch_cpu_unquantized_gemm(layer, remove_weight=False)
assert log_calls == [
(
"CPU unquantized GEMM dispatch: using zentorch_linear_unary (prepacked=%s)",
expected_prepacked,
)
]