From e9055c32f9f9d659e05665cb38c0d905cc158514 Mon Sep 17 00:00:00 2001 From: Jin Qiao <89779290+JinBridger@users.noreply.github.com> Date: Tue, 19 Mar 2024 16:17:23 +0800 Subject: [PATCH] LLM: fix fp16 mem record in benchmark (#10461) * LLM: fix fp16 mem record in benchmark * change style --- python/llm/dev/benchmark/all-in-one/run.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/llm/dev/benchmark/all-in-one/run.py b/python/llm/dev/benchmark/all-in-one/run.py index a01d18f0..4fa21e26 100644 --- a/python/llm/dev/benchmark/all-in-one/run.py +++ b/python/llm/dev/benchmark/all-in-one/run.py @@ -115,7 +115,7 @@ def run_model(repo_id, test_api, in_out_pairs, local_model_hub=None, warm_up=1, low_bit, cpu_embedding if 'win' in test_api else 'N/A', round(result[in_out_pair][-1][5], 2), - result[in_out_pair][-1][6] if 'int4_gpu' in test_api or 'int4_loadlowbit_gpu' in test_api else 'N/A', + result[in_out_pair][-1][6] if any(keyword in test_api for keyword in ['int4_gpu', 'int4_fp16_gpu_win', 'int4_loadlowbit_gpu' ]) else 'N/A', streaming if 'win' in test_api else 'N/A'], )