Merge branch 'volcengine:main' into ds_nokl

Author: zhaochenyang20

.github/CODEOWNERS

@@ -2,19 +2,21 @@
 /docs/amd_tutorial @yushengsu-thu
 /docs/slang_multiturn @zhaochenyang20 @SwordFaith
 
-/recipe/dapo @tongyx361 @PeterSH6
+/recipe/dapo @tongyx361 @PeterSH6 @vermouth1992 @tardis-key @FightingZhen @ji-huazhong
 /recipe/spin @zhaochenyang20
 /recipe/sppo @zhaochenyang20
 
 /third_party/sglang @zhaochenyang20 @SwordFaith
 /third_party/vllm @PeterSH6 @wuxibin89
+/examples/grpo_trainer @vermouth1992 @PeterSH6 @tardis-key @FightingZhen @ji-huazhong
 /verl/single_controller @zw0610 @wuxibin89 @hongpeng-guo
 /verl/trainer @eric-haibin-lin @vermouth1992 @tongyx361 @PeterSH6
 /verl/workers/engine @eric-haibin-lin @vermouth1992 @ZihengJiang
 /verl/workers/roles @eric-haibin-lin @vermouth1992 @ZihengJiang
 /verl/workers/engine/fsdp @eric-haibin-lin @vermouth1992 @ZihengJiang
 /verl/workers/rollout/vllm_rollout @wuxibin89 @PeterSH6 @chenhaiq
 /verl/workers/rollout/sglang_rollout @zhaochenyang20 @SwordFaith @chenhaiq
+/verl/models/transformers @vermouth1992 @PeterSH6 @tardis-key @FightingZhen @ji-huazhong
 
 /tests/single_controller @zw0610 @wuxibin89
 /tests/trainer @eric-haibin-lin @vermouth1992 @tongyx361 @PeterSH6

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -0,0 +1,65 @@
+# modified from https://github.com/huggingface/transformers/blob/main/.github/ISSUE_TEMPLATE/bug-report.yml?plain=1
+name: "\U0001F41B Bug Report"
+description: Submit a bug report to help us improve verl
+labels: [ "bug" ]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this bug report! 🤗
+
+  - type: textarea
+    id: system-info
+    attributes:
+      label: System Info
+      description: Please share your system info with us. You can run the command `python scripts/diagnose.py` and copy-paste its output below.
+      placeholder: verl version, platform, python version, ...
+    validations:
+      required: true
+
+  - type: checkboxes
+    id: information-scripts-examples
+    attributes:
+      label: Information
+      description: 'The problem arises when using:'
+      options:
+        - label: "The official example scripts"
+        - label: "My own modified scripts"
+
+  - type: checkboxes
+    id: information-tasks
+    attributes:
+      label: Tasks
+      description: "The tasks I am working on are:"
+      options:
+        - label: "An officially supported task in the `examples` folder (such as GLUE/SQuAD, ...)"
+        - label: "My own task or dataset (give details below)"
+
+  - type: textarea
+    id: reproduction
+    validations:
+      required: true
+    attributes:
+      label: Reproduction
+      description: |
+        Please provide a code sample that reproduces the problem you ran into. It can be a Colab link or just a code snippet.
+        Please include relevant config information with your code.
+        If you have code snippets, error messages, stack traces please provide them here as well.
+        Important! Use code tags to correctly format your code. See https://help.github.com/en/github/writing-on-github/creating-and-highlighting-code-blocks#syntax-highlighting
+        Do not use screenshots, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
+
+      placeholder: |
+        Steps to reproduce the behavior:
+
+          1.
+          2.
+          3.
+
+
+  - type: textarea
+    id: expected-behavior
+    validations:
+      required: true
+    attributes:
+      label: Expected behavior
+      description: "A clear and concise description of what you would expect to happen."

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,2 @@
+blank_issues_enabled: true
+version: 0.1

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -0,0 +1,32 @@
+# modified from https://github.com/huggingface/transformers/blob/main/.github/ISSUE_TEMPLATE/feature-request.yml?plain=1
+name: "\U0001F680 Feature request"
+description: Submit a proposal/request for a new verl feature
+labels: [ "Feature request" ]
+body:
+  - type: textarea
+    id: feature-request
+    validations:
+      required: true
+    attributes:
+      label: Feature request
+      description: |
+        A clear and concise description of the feature proposal. Please provide a link to the paper and code in case they exist.
+
+  - type: textarea
+    id: motivation
+    validations:
+      required: true
+    attributes:
+      label: Motivation
+      description: |
+        Please outline the motivation for the proposal. Is your feature request related to a problem? e.g., I'm always frustrated when [...]. If this is related to another GitHub issue, please link here too.
+
+
+  - type: textarea
+    id: contribution
+    validations:
+      required: true
+    attributes:
+      label: Your contribution
+      description: |
+        Is there any way that you could help, e.g. by submitting a PR? Make sure to read the CONTRIBUTING.MD [readme](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md)

.github/workflows/.deprecate/e2e_ppo_trainer.yml

@@ -89,7 +89,7 @@ jobs:
       - name: Prepare gsm8k dataset with tool
         run: |
           ray stop --force
-          python3 examples/data_preprocess/gsm8k_multiturn_w_tool.py --local_dir $HOME/data/gsm8k_verl_sgl_multi_turn_preprocessed
+          python3 examples/data_preprocess/gsm8k_multiturn_w_tool.py --local_save_dir $HOME/data/gsm8k_verl_sgl_multi_turn_preprocessed
       - name: Running GSM8K with tool E2E training tests on 8 L20 GPUs with rmpad using function rm and save ckpt with sglang
         run: |
           ray stop --force

.github/workflows/doc.yml

@@ -74,7 +74,7 @@ jobs:
           python-version: ${{ matrix.python-version }}
       - name: Install the current repository
         run: |
-          pip install -e .[test]
+          pip install -e .[test] --no-deps
           pip install -r docs/requirements-docs.txt
 
       - name: Run doc make html

.github/workflows/e2e_ascend.yml

@@ -143,6 +143,11 @@ jobs:
           ray stop --force
           bash tests/special_npu/run_qwen2_5_05b_dapo.sh
           rm -rf $HOME/ckpts
+      - name: Running gsm8k e2e qwen3 training tests with GRPO on ASCEND NPU
+        run: |
+          ray stop --force
+          bash tests/special_npu/run_qwen3_06b_grpo.sh
+          rm -rf $HOME/ckpts
       - name: Running gsm8k e2e training tests with GRPO MindSpeed on ASCEND NPU
         run: |
           ray stop --force
@@ -153,4 +158,3 @@ jobs:
         run: |
           ray stop --force
           pytest -s -x tests/utils/test_special_mstx_profile.py
-          

.github/workflows/e2e_ppo_trainer_megatron_sglang.yml

@@ -284,6 +284,7 @@ jobs:
       - name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (DeepSeek)
         run: |
           ray stop --force
+          MEGATRON_CI_DISABLE_EXPANDABLE_SEGMENTS=1 \
           ADV_ESTIMATOR=grpo USE_DUMMY_MODEL=True DUMMY_MODEL_CONFIG_PATH=tests/special_e2e/ppo_trainer/expert_parallel/qwen2moe_minimal.json \
           PPO_MAX_TOKEN_LEN=512 FWD_MAX_TOKEN_LEN=512 \
           MAX_PROMPT_LENGTH=256 MAX_RESPONSE_LENGTH=256 \

.github/workflows/e2e_sft.yml

@@ -70,7 +70,7 @@ permissions:
   contents: read
 
 env:
-  IMAGE: "verl-ci-cn-beijing.cr.volces.com/verlai/verl:base-verl0.5-cu126-cudnn9.8-torch2.7.1-fa2.7.4"
+  IMAGE: "verl-ci-cn-beijing.cr.volces.com/verlai/verl:app-verl0.5-transformers4.55.4-sglang0.4.10.post2-mcore0.13.0-te2.2"
   DYNAMIC_RUNNER_ENDPOINT: "https://sd10g3clalm04ug7alq90.apigateway-cn-beijing.volceapi.com/runner"
 
 jobs:
@@ -139,6 +139,14 @@ 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
+      - 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
+
   
   cleanup:
     runs-on: ubuntu-latest

.github/workflows/gpu_unit_tests.yml

@@ -100,7 +100,7 @@ jobs:
         # Disable requests to avoid network errors
       - name: Run all GPU unit tests
         run: |
-          pytest -s -x --ignore-glob="*test_special_*.py" --ignore-glob='*on_cpu.py' --ignore-glob="*test_vllm*" --ignore-glob="*_sglang*" --ignore-glob="*_hf_rollout*" --ignore-glob="tests/models/" --ignore-glob='tests/special*' --ignore-glob="tests/experimental" tests/
+          pytest -s -x --ignore-glob="*test_special_*.py" --ignore-glob='*on_cpu.py' --ignore-glob="*test_vllm*" --ignore-glob="*_sglang*" --ignore-glob="*_hf_rollout*" --ignore-glob="tests/models/" --ignore-glob='tests/special*' --ignore-glob="tests/experimental" --ignore-glob="tests/workers/reward_model" tests/
       - name: Testing LinearCrossEntropyTP Correctness, Computation Time and Memory Consumption
         run: |
           LOW_MEMORY=True torchrun --standalone --nnodes=1 --nproc-per-node=8 tests/utils/test_special_linear_cross_entropy_tp.py