[CPU][Zen] Update zentorch to 2.14.0.1 & enable float16 on Venice and later (#61411)

Signed-off-by: Ganesh R <ganesh.r@amd.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
Ganesh R
2026-10-15 00:23:50 -07:00
committed by GitHub
co-authored by Kevin H. Luu Cyrus Leung
parent 85c94c1706
commit 91ed2859c7
6 changed files with 27 additions and 6 deletions
+17
View File
@@ -2,9 +2,11 @@
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import builtins
import logging
from types import SimpleNamespace
from unittest.mock import mock_open, patch
import pytest
import torch
from vllm.platforms import (
_is_amd_zen_cpu,
@@ -139,3 +141,18 @@ def test_platform_plugin_failure_is_logged(caplog_vllm):
assert platform == "vllm.platforms.interface.UnspecifiedPlatform"
assert "Platform plugin cpu failed during detection" in caplog_vllm.text
assert "RuntimeError: plugin exploded" in caplog_vllm.text
@pytest.mark.parametrize("fp16_supported", [True, False])
def test_zen_cpu_supported_dtypes_track_fp16_capability(fp16_supported):
from vllm.platforms.zen_cpu import ZenCpuPlatform
# zentorch is absent on most CI hosts, so torch.ops.zentorch has to be
# stood up rather than patched in place.
zentorch_ops = SimpleNamespace(zentorch_is_fp16_supported=lambda: fp16_supported)
with patch.object(torch.ops, "zentorch", zentorch_ops, create=True):
dtypes = ZenCpuPlatform().supported_dtypes
# bf16 stays first so `--dtype auto` resolves to it on every Zen part.
assert dtypes[0] is torch.bfloat16
assert (torch.float16 in dtypes) is fp16_supported