Wanjuan

.github/CODEOWNERS

@@ -20,6 +20,7 @@
 /verl/workers/actor/megatron_actor.py @ISEEKYAN @vermouth1992
 /verl/workers/critic/megatron_critic.py @ISEEKYAN @vermouth1992
 /verl/workers/megatron_workers.py @ISEEKYAN @vermouth1992
+/verl/experimental @wuxibin89 @ArronHZG
 
 /tests/single_controller @zw0610 @wuxibin89
 /tests/trainer @eric-haibin-lin @vermouth1992 @tongyx361 @PeterSH6

.github/PULL_REQUEST_TEMPLATE.md

@@ -6,7 +6,7 @@
 
 - [ ] Search for similar PRs. Paste at least one query link here: ...
 - [ ] Format the PR title as `[{modules}] {type}: {description}` (This will be checked by the CI)
-  - `{modules}` include `fsdp`, `megatron`, `veomni`, `sglang`, `vllm`, `rollout`, `trainer`, `ci`, `training_utils`, `recipe`, `hardware`, `deployment`, `ray`, `worker`, `single_controller`, `misc`, `perf`, `model`, `algo`, `env`, `tool`, `ckpt`, `doc`, `data`, `cfg`, `reward`
+  - `{modules}` include `fsdp`, `megatron`, `veomni`, `sglang`, `vllm`, `rollout`, `trainer`, `ci`, `training_utils`, `recipe`, `hardware`, `deployment`, `ray`, `worker`, `single_controller`, `misc`, `perf`, `model`, `algo`, `env`, `tool`, `ckpt`, `doc`, `data`, `cfg`, `reward`, `fully_async`, `one_step_off`
   - If this PR involves multiple modules, separate them with `,` like `[megatron, fsdp, doc]`
   - `{type}` is in `feat`, `fix`, `refactor`, `chore`, `test`
   - If this PR breaks any API (CLI arguments, config, function signature, etc.), add `[BREAKING]` to the beginning of the title.

.github/workflows/e2e_ascend.yml

@@ -126,6 +126,10 @@ jobs:
           ray stop --force
           export PYTHONPATH=$PYTHONPATH:/Megatron-LM
           USE_DIST_CKPT=True USE_DUMMY_MODEL=True DUMMY_MODEL_CONFIG_PATH=tests/special_e2e/ppo_trainer/expert_parallel/qwen3moe_minimal.json DUMMY_MODEL_PATH=$HOME/dist_ckpt/qwen3_30b_grpo_mindspeed bash tests/special_npu/run_qwen3_30b_grpo_mindspeed.sh
+      - name: Running the E2E test with fully_async_policy algorithm (FSDP2)
+        run: |
+          ray stop --force
+          bash tests/special_npu/run_fully_async_policy.sh
 
   vlm_rl_job:
     if: github.repository_owner == 'verl-project'

.github/workflows/e2e_one_step_off_policy_ascend.yml

@@ -68,7 +68,7 @@ on:
       # Entrypoints
       - ".github/workflows/e2e_one_step_off_policy_ascend.yml"
       - "examples/data_preprocess/gsm8k.py"
-      - "tests/special_e2e/run_one_step_off_policy.sh"
+      - "tests/special_npu/run_one_step_off_policy.sh"
 
 # Cancel jobs on the same ref if a new one is triggered
 concurrency:
@@ -122,7 +122,7 @@ jobs:
       - name: Running the E2E test with one_step_off_policy algorithm (FSDP2)
         run: |
           ray stop --force
-          bash tests/special_e2e/run_one_step_off_policy.sh
+          bash tests/special_npu/run_one_step_off_policy.sh
 
   # Test Megatron strategy
   e2e_one_step_off_policy_megatron_ascend:
@@ -167,4 +167,4 @@ jobs:
         run: |
           ray stop --force
           export PYTHONPATH=$PYTHONPATH:/Megatron-LM
-          bash tests/special_e2e/run_one_step_off_policy.sh
+          bash tests/special_npu/run_one_step_off_policy.sh

.github/workflows/e2e_ppo_trainer_veomni_vllm.yml

@@ -134,7 +134,7 @@ jobs:
       - name: Running GEO3K E2E training tests on 8 L20 GPUs with veomni engine (FSDP_SIZE=8, USP=1)
         run: |
           ray stop --force
-          MODEL_ID=Qwen/Qwen3-VL-2B-Instruct TRAIN_FILES=${HOME}/data/geo3k/train.parquet VAL_FILES=${HOME}/data/gsm8k/test.parquet VAL_BEFORE_TRAIN=True NUM_GPUS=8 FSDP_SIZE=8 SP_SIZE=1 EP_SIZE=1 VERL_EXP_NAME="qwen3-2b-vl-function-reward-minimal-fsdp-size8" bash tests/special_e2e/run_ppo_trainer_veomni.sh
+          MODEL_ID=Qwen/Qwen3-VL-2B-Instruct TRAIN_FILES=${HOME}/data/geo3k/train.parquet VAL_FILES=${HOME}/data/gsm8k/test.parquet VAL_BEFORE_TRAIN=True NUM_GPUS=8 FSDP_SIZE=4 SP_SIZE=2 EP_SIZE=1 VERL_EXP_NAME="qwen3-2b-vl-function-reward-minimal-fsdp-size8" bash tests/special_e2e/run_ppo_trainer_veomni.sh
 
   cleanup:
     runs-on: ubuntu-latest

.github/workflows/e2e_sft_llm.yml

@@ -110,7 +110,7 @@ jobs:
       - name: Prepare gsm8k dataset
         run: |
           ray stop --force
-          python3 examples/data_preprocess/gsm8k.py --local_dataset_path ${HOME}/models/hf_data/gsm8k
+          python3 examples/data_preprocess/gsm8k_multiturn_sft.py --local_dataset_path ${HOME}/models/hf_data/gsm8k
       - name: Running GSM8K E2E training tests on 8 L20 GPUs with rmpad using function rm
         run: |
           ray stop --force
@@ -123,10 +123,6 @@ jobs:
         run: |
           ray stop --force
           SP_SIZE=2 bash tests/special_e2e/sft/run_sft.sh
-      - name: Check loss difference between sequence parallel vs. default implementation
-        run: |
-          ray stop --force
-          ENTRYPOINT="tests/special_e2e/sft/test_sp_loss_match.py" SP_SIZE=2 bash tests/special_e2e/sft/run_sft.sh
       - name: Running GSM8K E2E training tests on 8 L20 GPUs with sequence parallism and liger
         run: |
           ray stop --force
@@ -140,10 +136,6 @@ jobs:
           ray stop --force
           LORA_RANK=32 RESUME_MODE=auto TOTAL_TRAIN_STEP=2 bash tests/special_e2e/sft/run_sft.sh
       # TODO: multiturn
-      - name: Prepare gsm8k dataset
-        run: |
-          ray stop --force
-          python3 examples/data_preprocess/gsm8k_multiturn_sft.py --local_dataset_path ${HOME}/models/hf_data/gsm8k
       - name: Running GSM8K E2E training tests with multiturn and various configs and compare results
         run: |
           bash tests/special_e2e/sft/test_sft_engine_all.sh

.github/workflows/e2e_sft_llm_ascend.yml

@@ -109,7 +109,7 @@ jobs:
           ln -s /root/.cache/models ~/models
       - name: Prepare gsm8k dataset
         run: |
-          python examples/data_preprocess/gsm8k.py --local_dataset_path ${HOME}/.cache/datasets/openai/gsm8k
+          python3 examples/data_preprocess/gsm8k_multiturn_sft.py --local_dataset_path ${HOME}/.cache/datasets/openai/gsm8k
       - name: Running GSM8K E2E training tests on 8 NPUs with rmpad using function rm
         run: |
           ray stop --force
@@ -122,10 +122,6 @@ jobs:
         run: |
           ray stop --force
           SP_SIZE=2 bash tests/special_e2e/sft/run_sft.sh
-      - name: Check loss difference between sequence parallel vs. default implementation
-        run: |
-          ray stop --force
-          ENTRYPOINT="tests/special_e2e/sft/test_sp_loss_match.py" SP_SIZE=2 bash tests/special_e2e/sft/run_sft.sh
       - name: Running GSM8K E2E training tests with LoRA
         run: |
           ray stop --force
@@ -134,11 +130,6 @@ jobs:
         run: |
           ray stop --force
           LORA_RANK=32 RESUME_MODE=auto TOTAL_TRAIN_STEP=2 bash tests/special_e2e/sft/run_sft.sh
-      # TODO: multiturn
-      - name: Prepare gsm8k dataset
-        run: |
-          ray stop --force
-          python3 examples/data_preprocess/gsm8k_multiturn_sft.py --local_dataset_path ${HOME}/.cache/datasets/openai/gsm8k
       - name: Running GSM8K E2E training tests with multiturn and various configs and compare results
         run: |
           export PYTHONPATH=$PYTHONPATH:/Megatron-LM