[CPU] Experimentally enable Triton and MRV2 (#43225)

Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
Li, Jiang
2026-05-22 01:48:17 -07:00
committed by GitHub
parent 2380bfc210
commit 65b7a812a2
11 changed files with 169 additions and 13 deletions
+16
View File
@@ -0,0 +1,16 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from collections.abc import Sequence
import torch
from vllm.utils.platform_utils import is_uva_available
class UvaBuffer:
def __init__(self, size: int | Sequence[int], dtype: torch.dtype):
if not is_uva_available():
raise RuntimeError("UVA is not available")
self.cpu = torch.zeros(size, dtype=dtype, device="cpu")
self.np = self.cpu.numpy()
self.uva = self.cpu