From 8085e8b150829c73516545f901330fc7a3019b24 Mon Sep 17 00:00:00 2001 From: anandhu-eng Date: Tue, 3 Sep 2024 18:33:06 +0530 Subject: [PATCH] updated neural magic documentation --- main.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/main.py b/main.py index 77f10560d..c9e3e1b56 100755 --- a/main.py +++ b/main.py @@ -383,6 +383,7 @@ def mlperf_inference_run_command(spaces, model, implementation, framework, categ elif implementation == "neuralmagic": docker_cmd_suffix += f" \\\n{pre_space} --api_server=http://localhost:8000" docker_cmd_suffix += f" \\\n{pre_space} --vllm_model_name=nm-testing/Llama-2-70b-chat-hf-FP8" + docker_cmd_suffix += f" \\\n{pre_space} --adr.mlperf-implementation.tags=_repo.https://github.com/neuralmagic/inference,_branch.vllm" if "dlrm-v2" in model.lower() and implementation == "nvidia": docker_cmd_suffix += f" \\\n{pre_space} --criteo_day23_raw_data_path=" @@ -415,6 +416,7 @@ def mlperf_inference_run_command(spaces, model, implementation, framework, categ elif implementation == "neuralmagic": cmd_suffix += f" \\\n{pre_space} --api_server=http://localhost:8000" cmd_suffix += f" \\\n{pre_space} --vllm_model_name=nm-testing/Llama-2-70b-chat-hf-FP8" + cmd_suffix += f" \\\n{pre_space} --adr.mlperf-implementation.tags=_repo.https://github.com/neuralmagic/inference,_branch.vllm" if "dlrm-v2" in model and implementation == "nvidia": cmd_suffix += f" \\\n{pre_space} --criteo_day23_raw_data_path="