Skip to content
Draft
Changes from 1 commit
Commits
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
Next Next commit
add ci test shell
  • Loading branch information
Gary-cjy committed Feb 5, 2026
commit b7a34f21e19607dbd8a08f0b1a39783410e9a5a3
29 changes: 28 additions & 1 deletion tests/special_npu/run_qwen2_5_05b_grpo.sh
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,14 @@ set -x
MODEL_ID=${MODEL_ID:-Qwen/Qwen2.5-0.5B-Instruct}
MODEL_PATH=${MODEL_PATH:-${HOME}/.cache/models/${MODEL_ID}}

SAVE_PATH="your_path"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

critical

The SAVE_PATH is set to a placeholder "your_path". This is not a valid directory and will cause the script to fail, especially in a CI environment where such a path is unlikely to exist. Please use a valid, descriptive path for the output data.

Suggested change
SAVE_PATH="your_path"
SAVE_PATH="outputs/profile_qwen2_5_05b_grpo"

LEVEL="level1"
CONTENTS=['npu', 'cpu']
ANALYSIS=True
PROFILE_STEPS="[1]"
PROFILE_RANKS_ALL=True
DISCRETE=False

python3 -m verl.trainer.main_ppo \
algorithm.adv_estimator=grpo \
data.train_files=$HOME/data/gsm8k/train.parquet \
Expand Down Expand Up @@ -44,4 +52,23 @@ python3 -m verl.trainer.main_ppo \
trainer.save_freq=-1 \
trainer.test_freq=-1 \
trainer.total_epochs=1 \
trainer.total_training_steps=1 $@
trainer.total_training_steps=1 \
actor_rollout_ref.actor.profiler.enable=True \
actor_rollout_ref.actor.profiler.all_ranks=$PROFILE_RANKS_ALL \
actor_rollout_ref.actor.profiler.all_tool_config.npu.discrete=$DISCRETE \
actor_rollout_ref.actor.profiler.all_tool_config.npu.contents=$CONTENTS \
actor_rollout_ref.actor.profiler.all_tool_config.npu.level=$LEVEL \
actor_rollout_ref.actor.profiler.all_tool_config.npu.analysis=$ANALYSIS \
actor_rollout_ref.ref.profiler.enable=True \
actor_rollout_ref.ref.profiler.all_ranks=$PROFILE_RANKS_ALL \
actor_rollout_ref.ref.profiler.all_tool_config.npu.discrete=$DISCRETE \
actor_rollout_ref.ref.profiler.all_tool_config.npu.contents=$CONTENTS \
actor_rollout_ref.ref.profiler.all_tool_config.npu.level=$LEVEL \
actor_rollout_ref.ref.profiler.all_tool_config.npu.analysis=$ANALYSIS \
global_profiler.tool=npu \
global_profiler.steps=$PROFILE_STEPS \
global_profiler.save_path=$SAVE_PATH \
trainer.device=npu $@
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

trainer.device is not required, device type can be obtained automatically