[Frontend] Consolidate dev entrypoints. (#44170)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>

.buildkite/test-amd.yaml

@@ -1238,14 +1238,11 @@ steps:
   working_dir: "/vllm-workspace/tests"
   source_file_dependencies:
   - vllm/
-  - tests/entrypoints/rpc
-  - tests/entrypoints/serve/instrumentator
-  - tests/tool_use
+  - tests/entrypoints/serve
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/serve/instrumentator
-  - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/rpc
-  - pytest -v -s tool_use
+  - pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc
+  - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/serve/dev/rpc
 
 - label: Entrypoints Integration (API Server openai - Part 1) # TBD
   timeout_in_minutes: 180
@@ -1276,11 +1273,13 @@ steps:
   - tests/entrypoints/openai
   - tests/entrypoints/test_chat_utils
   - tests/entrypoints/generate
+  - tests/tool_use
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
   - pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
   - pytest -v -s entrypoints/test_chat_utils.py
   - pytest -v -s entrypoints/generate
+  - pytest -v -s tool_use
 
 - label: Entrypoints Integration (API Server openai - Part 3) # TBD
   timeout_in_minutes: 180
@@ -1370,7 +1369,7 @@ steps:
   - vllm/platforms/rocm.py
   commands:
   - pytest -v -s entrypoints/openai/tool_parsers
-  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/serve/instrumentator --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling  --ignore=entrypoints/speech_to_text --ignore=tests/entrypoints/generate
+  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/offline_mode --ignore=entrypoints/openai --ignore=entrypoints/serve --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling --ignore=entrypoints/speech_to_text --ignore=tests/entrypoints/generate
 
 - label: OpenAI API correctness # TBD
   timeout_in_minutes: 180
@@ -2747,14 +2746,11 @@ steps:
   working_dir: "/vllm-workspace/tests"
   source_file_dependencies:
   - vllm/
-  - tests/entrypoints/rpc
-  - tests/entrypoints/serve/instrumentator
-  - tests/tool_use
+  - tests/entrypoints/serve
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/serve/instrumentator
-  - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/rpc
-  - pytest -v -s tool_use
+  - pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc
+  - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/serve/dev/rpc
 
 - label: Entrypoints Integration (API Server openai - Part 1) # TBD
   timeout_in_minutes: 180
@@ -2785,11 +2781,13 @@ steps:
   - tests/entrypoints/openai
   - tests/entrypoints/test_chat_utils
   - tests/entrypoints/generate
+  - tests/tool_use
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
   - pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
   - pytest -v -s entrypoints/test_chat_utils.py
   - pytest -v -s entrypoints/generate
+  - pytest -v -s tool_use
 
 - label: Entrypoints Integration (API Server openai - Part 3) # TBD
   timeout_in_minutes: 180

.buildkite/test_areas/entrypoints.yaml

@@ -11,7 +11,7 @@ steps:
   - tests/entrypoints/
   commands:
   - pytest -v -s entrypoints/openai/tool_parsers
-  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/serve/instrumentator --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling --ignore=entrypoints/speech_to_text --ignore=tests/entrypoints/generate
+  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/offline_mode --ignore=entrypoints/openai --ignore=entrypoints/serve --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling --ignore=entrypoints/speech_to_text --ignore=tests/entrypoints/generate
 
 - label: Entrypoints Integration (LLM)
   key: entrypoints-integration-llm
@@ -61,10 +61,12 @@ steps:
   - tests/entrypoints/openai
   - tests/entrypoints/test_chat_utils
   - tests/entrypoints/generate
+  - tests/tool_use
   commands:
   - pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
   - pytest -v -s entrypoints/test_chat_utils.py
   - pytest -v -s entrypoints/generate
+  - pytest -v -s tool_use
   mirror:
     amd:
       device: mi325_1
@@ -100,14 +102,11 @@ steps:
   working_dir: "/vllm-workspace/tests"
   source_file_dependencies:
   - vllm/
-  - tests/entrypoints/rpc
-  - tests/entrypoints/serve/instrumentator
-  - tests/tool_use
+  - tests/entrypoints/serve
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/serve/instrumentator
-  - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/rpc
-  - pytest -v -s tool_use
+  - pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc
+  - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/serve/dev/rpc
   mirror:
     amd:
       device: mi325_1
@@ -155,6 +154,5 @@ steps:
   source_file_dependencies:
   - csrc/
   - vllm/entrypoints/openai/
-  - vllm/model_executor/models/whisper.py
   commands: # LMEval
   - pytest -s entrypoints/openai/correctness/

.buildkite/test_areas/rust_frontend.yaml

@@ -45,19 +45,19 @@ steps:
   - vllm/entrypoints/serve/
   - vllm/v1/engine/
   - tests/utils.py
-  # - tests/entrypoints/rpc/test_collective_rpc.py
+  # - tests/entrypoints/serve/dev/rpc/test_collective_rpc.py
   - tests/entrypoints/serve/disagg/test_serving_tokens.py
   - tests/entrypoints/serve/instrumentator/test_basic.py
   - tests/entrypoints/serve/instrumentator/test_metrics.py
-  # - tests/entrypoints/serve/instrumentator/test_sleep.py
+  # - tests/entrypoints/serve/dev/test_sleep.py
   commands:
   - export VLLM_USE_RUST_FRONTEND=1
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  # - pytest -v -s entrypoints/rpc/test_collective_rpc.py
+  # - pytest -v -s entrypoints/serve/dev/rpc/test_collective_rpc.py
   - pytest -v -s entrypoints/serve/instrumentator/test_basic.py -k "not show_version and not server_load"
   - pytest -v -s entrypoints/serve/disagg/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/instrumentator/test_sleep.py
+  # - pytest -v -s entrypoints/serve/dev/test_sleep.py
 
 - label: Rust Frontend Core Correctness
   timeout_in_minutes: 30