From 73dcb488a186d07acbed9ee8d36081bd010423f2 Mon Sep 17 00:00:00 2001 From: Crefeda Rodrigues Date: Tue, 31 Mar 2026 14:55:29 +0100 Subject: [PATCH] Enable llama3.1-8b on CPU Signed-off-by: Crefeda Rodrigues --- language/llama3.1-8b/SUT_VLLM.py | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/language/llama3.1-8b/SUT_VLLM.py b/language/llama3.1-8b/SUT_VLLM.py index 94ee14abdd..a26118f7fe 100644 --- a/language/llama3.1-8b/SUT_VLLM.py +++ b/language/llama3.1-8b/SUT_VLLM.py @@ -1,3 +1,19 @@ +# Copyright 2025 The MLPerf Authors. All Rights Reserved. +# Copyright 2026 Arm Limited and affiliates. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# ============================================================================= + import asyncio import os import time @@ -49,9 +65,6 @@ def __init__( self.dtype = dtype self.tensor_parallel_size = tensor_parallel_size - if not torch.cuda.is_available(): - assert False, "torch gpu is not available, exiting..." - self.dataset_path = dataset_path self.data_object = Dataset( self.model_path,