organize the code

intel-analytics · May 30, 2024 · f1e6271 · f1e6271
1 parent b77dbc9
commit f1e6271
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/python/llm/dev/benchmark/all-in-one/config.yaml b/python/llm/dev/benchmark/all-in-one/config.yaml
@@ -7,7 +7,8 @@ warm_up: 1 # must set >=2 when run "pipeline_parallel_gpu" test_api
 num_trials: 3
 num_beams: 1 # default to greedy search
 low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
-batch_size: 1 # default to 1
+batch_size: 
+  - 1 # default to 1
 in_out_pairs:
   - '32-32'
   - '1024-128'

diff --git a/python/llm/dev/benchmark/all-in-one/run.py b/python/llm/dev/benchmark/all-in-one/run.py
@@ -1822,7 +1822,7 @@ def run_pipeline_parallel_gpu(repo_id,
 
     import pandas as pd
     for api in conf.test_api:
-        for batch_size in conf["batch_size"]: # mwj might need to change
+        for batch_size in conf["batch_size"]:
             global csv_name
             batch = str(batch_size)
             csv_name = f'{current_dir}/test_batch{batch}/{api}-results-{today}-batch-{batch}.csv'