[CI][RL] Consolidate RL entrypoint tests under tests/entrypoints/rl (#59948)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

.buildkite/intel_jobs/entrypoints_intel.yaml

@@ -19,14 +19,14 @@ steps:
   source_file_dependencies:
   - vllm/entrypoints
   - tests/entrypoints/unit_tests
-  - tests/entrypoints/weight_transfer
+  - tests/entrypoints/rl/weight_transfer
   - tests/entrypoints/launchers
   commands:
   - >-
     bash .buildkite/scripts/hardware_ci/run-intel-test.sh
     'cd tests &&
     pytest -v -s entrypoints/unit_tests &&
-    pytest -v -s entrypoints/weight_transfer'
+    pytest -v -s entrypoints/rl/weight_transfer'
 
 - label: ":intel: (BMG) Entrypoints Integration (LLM)"
   key: entrypoints-integration-llm-intel
@@ -71,14 +71,17 @@ steps:
   - vllm/
   - "!vllm/distributed/kv_transfer/"
   - tests/entrypoints/serve
+  - tests/entrypoints/rl
   commands:
   - >-
     bash .buildkite/scripts/hardware_ci/run-intel-test.sh
     'export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
     cd tests &&
-    pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc
-    --ignore=entrypoints/serve/dev/rlhf/test_weight_operation_metrics.py
-    --deselect="tests/entrypoints/serve/dev/rlhf/state_transitions/test_pause_resume.py::TestPauseResume::test_clear_cache_preserves_output_and_controls_prefix_cache[MRV1]" &&
+    pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc &&
+    pytest -v -s entrypoints/rl --ignore=entrypoints/rl/weight_transfer
+    --ignore=entrypoints/rl/return_routed_experts/test_openai_api.py
+    --ignore=entrypoints/rl/test_weight_operation_metrics.py
+    --deselect="tests/entrypoints/rl/state_transitions/test_pause_resume.py::TestPauseResume::test_clear_cache_preserves_output_and_controls_prefix_cache[MRV1]" &&
     PYTHONPATH=/workspace/vllm pytest -v -s entrypoints/serve/dev/rpc'
 
 - label: ":intel: (BMG) Entrypoints Integration (API Server Scale Out)"

.buildkite/test-amd.yaml

@@ -1044,12 +1044,12 @@ steps:
   source_file_dependencies:
   - vllm/entrypoints
   - tests/entrypoints/unit_tests
-  - tests/entrypoints/weight_transfer
+  - tests/entrypoints/rl/weight_transfer
   - tests/entrypoints/launchers
   - vllm/platforms/rocm.py
   commands:
   - pytest -v -s entrypoints/unit_tests
-  - pytest -v -s entrypoints/weight_transfer
+  - pytest -v -s entrypoints/rl/weight_transfer
   - pytest -v -s entrypoints/launchers
 
 - label: ":amd: (MI300) Entrypoints Integration (Responses API)" # TBD
@@ -3746,11 +3746,13 @@ steps:
   - vllm/
   - tests/entrypoints/serve
   - tests/entrypoints/scale_out
+  - tests/entrypoints/rl
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
   - pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
   - if [ "$$BUILDKITE_PARALLEL_JOB" = "1" ]; then PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/serve/dev/rpc; fi
   - pytest -v -s entrypoints/scale_out --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
+  - pytest -v -s entrypoints/rl --ignore=entrypoints/rl/weight_transfer --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
 
 - label: ":amd: (MI355 DPX) Entrypoints Integration (OpenAI API completion)" # TBD
   timeout_in_minutes: 65

.buildkite/test_areas/entrypoints.yaml

@@ -31,11 +31,9 @@ steps:
   source_file_dependencies:
   - vllm/entrypoints
   - tests/entrypoints/unit_tests
-  - tests/entrypoints/weight_transfer
   - tests/entrypoints/launchers
   commands:
   - pytest -v -s entrypoints/unit_tests
-  - pytest -v -s entrypoints/weight_transfer
   - pytest -v -s entrypoints/launchers
   mirror:
     amd:

.buildkite/test_areas/rl.yaml

@@ -0,0 +1,25 @@
+group: RL
+depends_on: 
+  - image-build
+steps:
+- label: ":nvidia: (H200 MIG 35GB) RL Entrypoints"
+  device: h200_35gb
+  key: rl-entrypoints-tests
+  timeout_in_minutes: 40
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/
+  - "!vllm/distributed/kv_transfer/"
+  - tests/entrypoints/rl
+  commands:
+  - pytest -v -s entrypoints/rl/weight_transfer
+  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  - pytest -v -s entrypoints/rl --ignore=entrypoints/rl/weight_transfer
+  mirror:
+    amd:
+      label: ":amd: (MI355 DPX) RL Entrypoints"
+      dind: false
+      device: mi355_dpx
+      timeout_in_minutes: 50
+      depends_on:
+      - image-build-amd

.buildkite/test_areas/rust_frontend.yaml

@@ -82,7 +82,6 @@ steps:
   - tests/entrypoints/scale_out/token_in_token_out/test_serving_tokens.py
   - tests/entrypoints/serve/instrumentator/test_basic.py
   - tests/entrypoints/serve/instrumentator/test_metrics.py
-  # - tests/entrypoints/serve/dev/test_sleep.py
   - tests/entrypoints/serve/tokenize/test_tokenization.py
   commands:
   - export VLLM_USE_RUST_FRONTEND=1
@@ -93,7 +92,6 @@ steps:
   # test_generate_logprobs expects Python-style top_logprobs truncation (dedup sampled + cap at max(k, 1)).
   - pytest -v -s entrypoints/scale_out/token_in_token_out/test_serving_tokens.py -k "not stream and not lora and not test_generate_logprobs and not stop_string_workflow"
   - pytest -v -s entrypoints/serve/instrumentator/test_metrics.py -k "text and not show and not run_batch and not test_metrics_counts and not test_metrics_exist"
-  # - pytest -v -s entrypoints/serve/dev/test_sleep.py
   # /tokenizer_info is not implemented in the Rust frontend (the CLI flag is accepted as a no-op).
   - pytest -v -s entrypoints/serve/tokenize/test_tokenization.py -k "not tokenizer_info"
   mirror:

.github/CODEOWNERS

@@ -231,8 +231,7 @@ mkdocs.yaml @hmellor
 /vllm/distributed/weight_transfer @aoshen02
 /vllm/entrypoints/serve/dev/rlhf @njhill @aoshen02
 /tests/distributed/test_weight_transfer.py @aoshen02
-/tests/entrypoints/weight_transfer @DarkLight1337 @robertgshaw2-redhat @aarnphm @NickLucche @AndreasKaratzas @aoshen02
-/tests/entrypoints/serve/dev/rlhf @DarkLight1337 @robertgshaw2-redhat @aarnphm @NickLucche @AndreasKaratzas @aoshen02
+/tests/entrypoints/rl @DarkLight1337 @robertgshaw2-redhat @njhill @aarnphm @NickLucche @AndreasKaratzas @aoshen02
 /tests/v1/worker/test_gpu_worker_weight_transfer.py @aoshen02
 /examples/rl @aoshen02
 /docs/training/rlhf.md @aoshen02

tests/entrypoints/rl/return_routed_experts/test_openai_api.py

@@ -7,7 +7,7 @@ import numpy as np
 import pybase64 as base64
 import pytest
 
-from ...utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
 
 MODEL_NAME = "TitanML/tiny-mixtral"
 

tests/entrypoints/rl/state_transitions/test_pause_resume.py

@@ -10,7 +10,7 @@ from unittest.mock import patch
 import pytest
 import requests
 
-from tests.entrypoints.serve.dev.rlhf.conftest import (
+from tests.entrypoints.rl.conftest import (
     cached_tokens,
     completion_with_cache_details,
     gen,

tests/entrypoints/rl/state_transitions/test_weight_checker.py

@@ -9,7 +9,7 @@ import requests
 import torch
 from transformers import AutoModelForCausalLM
 
-from tests.entrypoints.serve.dev.rlhf.conftest import (
+from tests.entrypoints.rl.conftest import (
     MODEL_NAME,
     gen,
     health,

tests/entrypoints/rl/test_weight_operation_metrics.py

@@ -7,7 +7,7 @@ import torch
 from prometheus_client.parser import text_string_to_metric_families
 from transformers import AutoModelForCausalLM
 
-from tests.entrypoints.serve.dev.rlhf.conftest import MODEL_NAME
+from tests.entrypoints.rl.conftest import MODEL_NAME
 from tests.utils import RemoteOpenAIServer
 from vllm.distributed.weight_transfer import (
     HTTPVLLMWeightSyncClient,

tests/entrypoints/rl/weight_transfer/test_offline.py

@@ -15,6 +15,7 @@ from unittest.mock import patch
 import pytest
 import torch
 
+from tests.utils import create_new_process_for_each_test
 from vllm.config import WeightTransferConfig
 from vllm.distributed.weight_transfer.base import (
     WeightTransferEngine,
@@ -24,8 +25,6 @@ from vllm.distributed.weight_transfer.base import (
     WeightTransferUpdateRequest,
 )
 
-from ...utils import create_new_process_for_each_test
-
 # Use a tiny model for fast testing
 MODEL_NAME = "hmellor/tiny-random-LlamaForCausalLM"
 

tests/entrypoints/scale_out/token_in_token_out/test_serving_multimodal_tokens.py

@@ -5,8 +5,8 @@
 Mirrors test_serving_tokens.py but exercises the multimodal piping
 using Qwen/Qwen3-VL-2B-Instruct end-to-end via the server's /render ->
 /generate -> /detokenize path. Intentionally avoids running the HF
-processor in the pytest parent process to keep os.fork() in sibling
-tests (e.g. test_weight_transfer_llm.py) deadlock-free.
+processor in the pytest parent process to keep os.fork() in other
+tests (e.g. entrypoints/rl/weight_transfer/test_offline.py) deadlock-free.
 """
 
 import httpx

tools/pre_commit/mypy.py

@@ -38,10 +38,10 @@ SILENT_GROUPS = [
     "tests/entrypoints/generate",
     "tests/entrypoints/multimodal",
     "tests/entrypoints/pooling",
+    "tests/entrypoints/rl",
     "tests/entrypoints/serve",
     "tests/entrypoints/tool_parsers",
     "tests/entrypoints/unit_tests",
-    "tests/entrypoints/weight_transfer",
     "tests/kernels/attention",
     "tests/kernels/core",
     "tests/kernels/helion",