Minor fixes

Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>

Author: kaiyux

examples/disaggregated/slurm/benchmark/config.yaml

@@ -5,7 +5,7 @@ slurm:
   account: "<account>"
   job_time: "02:00:00"
   job_name: "<job_name>"
-  extra_args: ""
+  extra_args: "" # Cluster specific arguments, e.g. "--gres=gpu:4 --exclude=node1,node2"
   numa_bind: true # Only enable for GB200 NVL72
 
 # Benchmark Mode

examples/disaggregated/slurm/benchmark/submit.py

@@ -130,15 +130,14 @@ def submit_job(config):
     cmd = [
         'sbatch',
         f'--partition={slurm_config["partition"]}',
-        f'--gres=gpu:{hw_config["gpus_per_node"]}',
         f'--account={slurm_config["account"]}',
         f'--time={slurm_config["job_time"]}',
         f'--job-name={slurm_config["job_name"]}',
         f'--nodes={total_nodes}',
         f'--ntasks={total_tasks}',
         f'--ntasks-per-node={hw_config["gpus_per_node"]}',
         f'--segment={total_nodes}',
-        slurm_config['extra_args'],
+        *([arg for arg in slurm_config['extra_args'].split() if arg]),
         slurm_config['script_file'],
         # Hardware configuration
         str(hw_config['gpus_per_node']),