Skip to content

Merge from go #118

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
arjunsuresh merged 2 commits into from
Jul 17, 2024
Merged

Merge from go #118

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7880a41
support num_workers in LLAMA2
arjunsuresh Jul 17, 2024
e26d6ca
Merge branch 'mlcommons:mlperf-inference' into mlperf-inference
arjunsuresh Jul 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions script/app-mlperf-inference-mlcommons-python/customize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -297,6 +297,7 @@ def get_run_cmd_reference(os_info, env, scenario_extra_options, mode_extra_optio
env['RUN_DIR'] = os.path.join(env['CM_MLPERF_INFERENCE_SOURCE'], "language", "llama2-70b")
backend = env['CM_MLPERF_BACKEND']
device = env['CM_MLPERF_DEVICE'] if env['CM_MLPERF_DEVICE'] != "gpu" else "cuda"

cmd = env['CM_PYTHON_BIN_WITH_PATH'] + " main.py " \
" --scenario " + env['CM_MLPERF_LOADGEN_SCENARIO'] + \
" --dataset-path " + env['CM_DATASET_PREPROCESSED_PATH'] + \
Expand All @@ -305,12 +306,17 @@ def get_run_cmd_reference(os_info, env, scenario_extra_options, mode_extra_optio
scenario_extra_options + mode_extra_options + \
" --output-log-dir " + env['CM_MLPERF_OUTPUT_DIR'] + \
' --dtype ' + env['CM_MLPERF_MODEL_PRECISION']

if env.get('CM_MLPERF_INFERENCE_API_SERVER', '') != '':
env['CM_VLLM_SERVER_MODEL_NAME'] = env.get("CM_VLLM_SERVER_MODEL_NAME") or "NousResearch/Meta-Llama-3-8B-Instruct"
#env['CM_MLPERF_INFERENCE_API_SERVER'] = "http://localhost:8000"
cmd += f" --api-server {env['CM_MLPERF_INFERENCE_API_SERVER']} --model-path {env['CM_VLLM_SERVER_MODEL_NAME']} --api-model-name {env['CM_VLLM_SERVER_MODEL_NAME']} --vllm "
else:
cmd += f" --model-path {env['MODEL_DIR']}"

if env.get('CM_MLPERF_INFERENCE_NUM_WORKERS', '') != '':
cmd += f" --num-workers {env['CM_MLPERF_INFERENCE_NUM_WORKERS']}"

cmd = cmd.replace("--count", "--total-sample-count")

elif "mixtral-8x7b" in env['CM_MODEL']:
Expand Down
1 change: 1 addition & 0 deletions script/run-mlperf-inference-app/_cm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,6 +100,7 @@ input_mapping:
nvidia_llama2_dataset_file_path: CM_NVIDIA_LLAMA_DATASET_FILE_PATH
tp_size: CM_NVIDIA_TP_SIZE
vllm_model_name: CM_VLLM_SERVER_MODEL_NAME
num_workers: CM_MLPERF_INFERENCE_NUM_WORKERS

new_state_keys:
- app_mlperf_inference_*
Expand Down