[trainer, fsdp, vllm, recipe] feat: one step off async training recipe

.github/workflows/e2e_one_step_off_policy.yml

@@ -0,0 +1,144 @@
+# # Tests layout
+
+# Each folder under tests/ corresponds to a test category for a sub-namespace in verl. For instance:
+# - `tests/trainer` for testing functionality related to `verl/trainer`
+# - `tests/models` for testing functionality related to `verl/models`
+# - ...
+
+# There are a few folders with `special_` prefix, created for special purposes:
+# - `special_distributed`: unit tests that must run with multiple GPUs
+# - `special_e2e`: end-to-end tests with training/generation scripts
+# - `special_npu`: tests for NPUs
+# - `special_sanity`: a suite of quick sanity tests
+# - `special_standalone`: a set of test that are designed to run in dedicated environments
+
+# Accelerators for tests
+# - By default tests are run with GPU available, except for the ones under `special_npu`, and any test script whose name ends with `on_cpu.py`.
+# - For test scripts with `on_cpu.py` name suffix would be tested on CPU resources in linux environment.
+
+# # Workflow layout
+
+# All CI tests are configured by yaml files in `.github/workflows/`. Here's an overview of all test configs:
+# 1. A list of always triggered CPU sanity tests: `check-pr-title.yml`, `secrets_scan.yml`, `check-pr-title,yml`, `pre-commit.yml`, `doc.yml`
+# 2. Some heavy multi-GPU unit tests, such as `model.yml`, `vllm.yml`, `sgl.yml`
+# 3. End-to-end tests: `e2e_*.yml`
+# 4. Unit tests
+#   - `cpu_unit_tests.yml`, run pytest on all scripts with file name pattern `tests/**/test_*_on_cpu.py`
+#   - `gpu_unit_tests.yml`, run pytest on all scripts with file without the `on_cpu.py` suffix.
+#   - Since cpu/gpu unit tests by default runs all tests under `tests`, please make sure tests are manually excluded in them when
+#     - new workflow yaml is added to `.github/workflows`
+#     - new tests are added to workflow mentioned in 2.
+
+
+name: e2e_one_step_off_policy
+
+on:
+  # Trigger the workflow on push or pull request,
+  # but only for the main branch
+  # For push, for now only anti-patterns are specified so it is more conservative
+  # and achieves higher coverage.
+  push:
+    branches:
+      - main
+      - v0.*
+    paths:
+      - "**/*.py"
+      - "!**/*.md"
+      - "!**/*.sh"
+      # Other entrypoints
+      - "!examples/*trainer*"
+      - "!tests/**"
+      - "!verl/trainer/main_*.py"
+      - "!verl/trainer/fsdp_sft_trainer.py"
+      - "!recipe/**"
+      - "recipe/one_step_off_policy"
+  pull_request:
+    branches:
+      - main
+      - v0.*
+    paths:
+      - "**/*.py"
+      - "!**/*.md"
+      - "!**/*.sh"
+      # Other entrypoints
+      - "!examples/**"
+      - "!tests/**"
+      - "!verl/trainer/main_*.py"
+      - "!verl/trainer/fsdp_sft_trainer.py"
+      # Other recipes
+      - "!recipe/**"
+      # Home
+      - "recipe/one_step_off_policy"
+      # Entrypoints
+      - ".github/workflows/e2e_one_step_off_policy.yml"
+      - "examples/data_preprocess/gsm8k.py"
+      - "tests/special_e2e/run_one_step_off_policy.sh"
+
+# Cancel jobs on the same ref if a new one is triggered
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+# Declare permissions just read content.
+permissions:
+  contents: read
+
+jobs:
+  # Test FSDP2 strategy
+  e2e_one_step_off_policy_fsdp2:
+    runs-on: [L20x8]
+    timeout-minutes: 50 # Increase timeout for async training
+    env:
+      HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
+      HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
+      NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
+      HF_ENDPOINT: "https://hf-mirror.com"
+      HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
+      ACTOR_STRATEGY: "fsdp2"
+    container:
+      image: verlai/verl:app-verl0.4-vllm0.8.5-mcore0.12.1
+      options: --gpus all --shm-size=10g
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          fetch-depth: 0
+      - name: Install the current repository
+        run: |
+          pip3 install --no-deps -e .[test,gpu]
+      - name: Prepare GSM8K dataset
+        run: |
+          python3 examples/data_preprocess/gsm8k.py
+      - 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
+
+  # Test Megatron strategy
+  e2e_one_step_off_policy_megatron:
+    runs-on: [L20x8]
+    timeout-minutes: 50 # Increase timeout for async training
+    env:
+      HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
+      HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
+      NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
+      HF_ENDPOINT: "https://hf-mirror.com"
+      HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
+      ACTOR_STRATEGY: "megatron"
+    container:
+      image: verlai/verl:app-verl0.4-vllm0.8.5-mcore0.12.1
+      options: --gpus all --shm-size=10g
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          fetch-depth: 0
+      - name: Install the current repository
+        run: |
+          pip3 install --no-deps -e .[test,gpu]
+      - name: Prepare GSM8K dataset
+        run: |
+          python3 examples/data_preprocess/gsm8k.py
+      - name: Running the E2E test with one_step_off_policy algorithm (Megatron)
+        run: |
+          ray stop --force
+          bash tests/special_e2e/run_one_step_off_policy.sh
+