b200 test

Author: Oseltamivir

.github/workflows/eval-gms8k.yml

@@ -42,7 +42,7 @@ on:
     paths:
       - '.github/workflows/eval-gms8k.yml'
       - '.github/workflows/eval-tmpl.yml' 
-      - 'benchmarks/benchmark_lib.sh' 
+      - 'benchmarks/benchmark_lib.sh'  
 
 jobs:
   eval:

runners/launch_b200-nvd.sh

@@ -35,6 +35,10 @@ else
   export NUM_PROMPTS=$(( CONC * 10 ))
 fi
 
+cd repo
+ls -lt
+rm -rf /home/nvadmin/actions-runner/_work/InferenceMAX/InferenceMAX/gpt-oss-120b/
+
 docker run --rm --init --network host --name $server_name \
 --runtime nvidia --gpus all --ipc host --privileged --shm-size=16g --ulimit memlock=-1 --ulimit stack=67108864 \
 -v $HF_HUB_CACHE_MOUNT:$HF_HUB_CACHE \