[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 vllm.logger import init_logger
from vllm.v1.worker.gpu.model_runner import GPUModelRunner
logger = init_logger(__name__)
class CPUModelRunner(GPUModelRunner):
# TBD: Whether need to move this to Worker?
def warming_up_model(self) -> None:
logger.info("Warming up model for the compilation...")
# Only generate graph for the generic shape
self.profile_run()
logger.info("Warming up done.")