From 996222f4bffc7b0c1e50bb18b42e9f0f09867d7b Mon Sep 17 00:00:00 2001 From: "wang.yuqi" Date: Tue, 9 Jun 2026 15:46:11 +0800 Subject: [PATCH] [CI] Reorganize entrypoints CI (#44947) Signed-off-by: wang.yuqi --- .buildkite/test-amd.yaml | 163 +++++++++--------- .buildkite/test_areas/entrypoints.yaml | 150 ++++++++-------- .buildkite/test_areas/plugins.yaml | 6 +- tests/distributed/test_distributed_oot.py | 2 +- .../{openai => }/tool_parsers/__init__.py | 0 .../tool_parsers/test_granite4_tool_parser.py | 2 +- .../tool_parsers/test_hermes_tool_parser.py | 3 +- .../tool_parsers/test_openai_tool_parser.py | 2 +- .../unit_tests}/__init__.py | 0 .../test_api_server_process_manager.py | 0 .../{ => unit_tests}/test_chat_utils.py | 0 .../{ => unit_tests}/test_context.py | 0 .../{ => unit_tests}/test_grpc_health.py | 0 .../{ => unit_tests}/test_launch_cli.py | 0 tests/plugins_tests/__init__.py | 0 .../plugins_tests/lora_resolvers/__init__.py | 0 .../test_filesystem_resolver.py | 0 .../lora_resolvers/test_hf_hub_resolver.py | 0 .../test_oot_registration_offline.py} | 3 +- .../test_oot_registration_online.py} | 0 20 files changed, 166 insertions(+), 165 deletions(-) rename tests/entrypoints/{openai => }/tool_parsers/__init__.py (100%) rename tests/entrypoints/{openai => }/tool_parsers/test_granite4_tool_parser.py (99%) rename tests/entrypoints/{openai => }/tool_parsers/test_hermes_tool_parser.py (99%) rename tests/entrypoints/{openai => }/tool_parsers/test_openai_tool_parser.py (99%) rename tests/{plugins/lora_resolvers => entrypoints/unit_tests}/__init__.py (100%) rename tests/entrypoints/{ => unit_tests}/test_api_server_process_manager.py (100%) rename tests/entrypoints/{ => unit_tests}/test_chat_utils.py (100%) rename tests/entrypoints/{ => unit_tests}/test_context.py (100%) rename tests/entrypoints/{ => unit_tests}/test_grpc_health.py (100%) rename tests/entrypoints/{ => unit_tests}/test_launch_cli.py (100%) create mode 100644 tests/plugins_tests/__init__.py create mode 100644 tests/plugins_tests/lora_resolvers/__init__.py rename tests/{plugins => plugins_tests}/lora_resolvers/test_filesystem_resolver.py (100%) rename tests/{plugins => plugins_tests}/lora_resolvers/test_hf_hub_resolver.py (100%) rename tests/{models/test_oot_registration.py => plugins_tests/test_oot_registration_offline.py} (98%) rename tests/{entrypoints/openai/chat_completion/test_oot_registration.py => plugins_tests/test_oot_registration_online.py} (100%) diff --git a/.buildkite/test-amd.yaml b/.buildkite/test-amd.yaml index 8191a7e303..fc0aa84a5b 100644 --- a/.buildkite/test-amd.yaml +++ b/.buildkite/test-amd.yaml @@ -88,16 +88,16 @@ # - Do NOT remove `VLLM_WORKER_MULTIPROC_METHOD=spawn` setting as ROCm requires this for certain models to function. # # * [Transformers Nightly Models]: Whisper needs `VLLM_WORKER_MULTIPROC_METHOD=spawn` to avoid deadlock. # # * [Plugin Tests (2 GPUs)]: # -# - {`pytest -v -s entrypoints/openai/test_oot_registration.py`}: It needs a clean process # -# - {`pytest -v -s models/test_oot_registration.py`}: It needs a clean process # -# - {`pytest -v -s plugins/lora_resolvers`}: Unit tests for in-tree lora resolver plugins # +# - {`pytest -v -s plugins_tests/test_oot_registration_online.py`}: It needs a clean process # +# - {`pytest -v -s plugins_tests/test_oot_registration_offline.py`}: It needs a clean process # +# - {`pytest -v -s plugins_tests/lora_resolvers`}: Unit tests for in-tree lora resolver plugins # # * [LoRA TP (Distributed)]: # # - There is some Tensor Parallelism related processing logic in LoRA that requires multi-GPU testing for validation. # # - {`pytest -v -s -x lora/test_gptoss_tp.py`}: Disabled for now because MXFP4 backend on non-cuda platform doesn't support # # LoRA yet. # # * [Distributed Tests (NxGPUs)(HW-TAG)]: Don't test llama model here, it seems hf implementation is buggy. See: # # https://github.com/vllm-project/vllm/pull/5689 # -# * [Distributed Tests (NxGPUs)(HW-TAG)]: Some old E2E tests were removed in https://github.com/vllm-project/vllm/pull/33293 # +# * [Distributed Tests (NxGPUs)(HW-TAG)]: Some old E2E tests were removed in https://github.com/vllm-project/vllm/pull/33293 # # in favor of new tests in fusions_e2e. We avoid replicating the new jobs in # # this file as it's deprecated. # # # @@ -617,9 +617,9 @@ steps: - pytest -v -s plugins_tests/test_scheduler_plugins.py - pip install -e ./plugins/vllm_add_dummy_model - pytest -v -s distributed/test_distributed_oot.py - - pytest -v -s entrypoints/openai/chat_completion/test_oot_registration.py - - pytest -v -s models/test_oot_registration.py - - pytest -v -s plugins/lora_resolvers + - pytest -v -s plugins_tests/test_oot_registration_online.py # it needs a clean process + - pytest -v -s plugins_tests/test_oot_registration_offline.py # it needs a clean process + - pytest -v -s plugins_tests/lora_resolvers # unit tests for in-tree lora resolver plugins #------------------------------------------------------------ mi250 · v1 -------------------------------------------------------------# @@ -1187,7 +1187,39 @@ steps: #-------------------------------------------------------- mi300 · entrypoints --------------------------------------------------------# -- label: Entrypoints Integration (API Server 2) # TBD +- label: Entrypoints Unit Tests # TBD + timeout_in_minutes: 180 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + agent_pool: mi300_1 + fast_check: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/entrypoints + - tests/entrypoints/unit_tests + - tests/entrypoints/weight_transfer + - vllm/platforms/rocm.py + commands: + - pytest -v -s entrypoints/unit_tests + - pytest -v -s entrypoints/weight_transfer + +- label: Entrypoints Integration (LLM) # TBD + timeout_in_minutes: 180 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + agent_pool: mi300_1 + optional: true + fast_check: true + torch_nightly: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/entrypoints/llm + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_collective_rpc.py --ignore=entrypoints/llm/offline_mode + - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process + - pytest -v -s entrypoints/llm/offline_mode # Needs to avoid interference with other tests + +- label: Entrypoints Integration (API Server) # TBD timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] agent_pool: mi300_1 @@ -1203,7 +1235,7 @@ steps: - 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 +- label: Entrypoints Integration (API Server OpenAI - Part 1) # TBD timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] agent_pool: mi300_1 @@ -1217,30 +1249,26 @@ steps: - tests/entrypoints/test_chat_utils commands: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s entrypoints/openai/chat_completion --ignore=entrypoints/openai/chat_completion/test_oot_registration.py + - pytest -v -s entrypoints/openai/ --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/correctness -- label: Entrypoints Integration (API Server openai - Part 2) # TBD +- label: Entrypoints Integration (API Server OpenAI - Part 2) # TBD timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] agent_pool: mi300_1 - optional: true fast_check: true torch_nightly: true + optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: - vllm/ - 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/chat_completion - 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 +- label: Entrypoints Integration (API Server Generate) # TBD timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] agent_pool: mi300_1 @@ -1250,11 +1278,30 @@ steps: working_dir: "/vllm-workspace/tests" source_file_dependencies: - vllm/ - - tests/entrypoints/openai - - tests/entrypoints/test_chat_utils + - tests/tool_use + - tests/entrypoints/tool_parsers + - tests/entrypoints/anthropic + - tests/entrypoints/generate commands: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/test_multi_api_servers.py + - pytest -v -s tool_use + - pytest -v -s entrypoints/tool_parsers + - pytest -v -s entrypoints/generate + - pytest -v -s entrypoints/anthropic + +- label: Entrypoints Integration (Responses API) # TBD + timeout_in_minutes: 180 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + agent_pool: mi300_1 + fast_check: true + torch_nightly: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/entrypoints/openai/responses + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s entrypoints/openai/responses - label: Entrypoints Integration (Speech to Text) # TBD timeout_in_minutes: 180 @@ -1284,23 +1331,6 @@ steps: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s entrypoints/multimodal -- label: Entrypoints Integration (LLM) # TBD - timeout_in_minutes: 180 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - agent_pool: mi300_1 - optional: true - fast_check: true - torch_nightly: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/entrypoints/llm - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_collective_rpc.py --ignore=entrypoints/llm/offline_mode - - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process - - pytest -v -s entrypoints/llm/offline_mode # Needs to avoid interference with other tests - - label: Entrypoints Integration (Pooling) # TBD timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -1315,34 +1345,6 @@ steps: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s entrypoints/pooling -- label: Entrypoints Integration (Responses API) # TBD - timeout_in_minutes: 180 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - agent_pool: mi300_1 - fast_check: true - torch_nightly: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/entrypoints/openai/responses - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s entrypoints/openai/responses - -- label: Entrypoints Unit Tests # TBD - timeout_in_minutes: 180 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - agent_pool: mi300_1 - fast_check: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/entrypoints - - tests/entrypoints/ - - vllm/platforms/rocm.py - commands: - - pytest -v -s entrypoints/openai/tool_parsers - - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/openai --ignore=entrypoints/serve --ignore=entrypoints/test_chat_utils.py --ignore=entrypoints/pooling --ignore=entrypoints/speech_to_text --ignore=entrypoints/pooling --ignore=entrypoints/multimodal --ignore=entrypoints/generate - - label: OpenAI API correctness # TBD timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -1352,7 +1354,6 @@ steps: source_file_dependencies: - csrc/ - vllm/entrypoints/openai/ - - vllm/model_executor/models/whisper.py - vllm/model_executor/layers/ - vllm/v1/attention/backends/ - vllm/v1/attention/selector.py @@ -2797,7 +2798,7 @@ steps: #-------------------------------------------------------- mi355 · entrypoints --------------------------------------------------------# -- label: Entrypoints Integration (API Server 2) # TBD +- label: Entrypoints Integration (API Server) # TBD timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] agent_pool: mi355_1 @@ -2813,7 +2814,7 @@ steps: - 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 +- label: Entrypoints Integration (API Server OpenAI - Part 1) # TBD timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] agent_pool: mi355_1 @@ -2827,9 +2828,9 @@ steps: - tests/entrypoints/test_chat_utils commands: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s entrypoints/openai/chat_completion --ignore=entrypoints/openai/chat_completion/test_oot_registration.py + - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/correctness -- label: Entrypoints Integration (API Server openai - Part 2) # TBD +- label: Entrypoints Integration (API Server OpenAI - Part 2) # TBD timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] agent_pool: mi355_1 @@ -2841,29 +2842,31 @@ steps: - vllm/ - 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/chat_completion - 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 +- label: Entrypoints Integration (API Server Generate) # TBD timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] agent_pool: mi355_1 fast_check: true torch_nightly: true + optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: - vllm/ - - tests/entrypoints/openai - - tests/entrypoints/test_chat_utils + - tests/tool_use + - tests/entrypoints/tool_parsers + - tests/entrypoints/anthropic + - tests/entrypoints/generate commands: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/test_multi_api_servers.py + - pytest -v -s tool_use + - pytest -v -s entrypoints/tool_parsers + - pytest -v -s entrypoints/generate + - pytest -v -s entrypoints/anthropic - label: Entrypoints Integration (Speech to Text) # TBD timeout_in_minutes: 180 diff --git a/.buildkite/test_areas/entrypoints.yaml b/.buildkite/test_areas/entrypoints.yaml index e76b2e1769..4dc6d7b0e8 100644 --- a/.buildkite/test_areas/entrypoints.yaml +++ b/.buildkite/test_areas/entrypoints.yaml @@ -8,10 +8,11 @@ steps: working_dir: "/vllm-workspace/tests" source_file_dependencies: - vllm/entrypoints - - tests/entrypoints/ + - tests/entrypoints/unit_tests + - tests/entrypoints/weight_transfer commands: - - pytest -v -s entrypoints/openai/tool_parsers - - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/openai --ignore=entrypoints/serve --ignore=entrypoints/test_chat_utils.py --ignore=entrypoints/pooling --ignore=entrypoints/speech_to_text --ignore=entrypoints/multimodal --ignore=entrypoints/generate + - pytest -v -s entrypoints/unit_tests + - pytest -v -s entrypoints/weight_transfer - label: Entrypoints Integration (LLM) key: entrypoints-integration-llm @@ -31,68 +32,9 @@ steps: depends_on: - image-build-amd -- label: Entrypoints Integration (API Server openai - Part 1) - key: entrypoints-integration-api-server-openai-part-1 - timeout_in_minutes: 50 - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/entrypoints/openai - - tests/entrypoints/test_chat_utils - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s entrypoints/openai/chat_completion --ignore=entrypoints/openai/chat_completion/test_oot_registration.py - mirror: - amd: - device: mi300_1 - timeout_in_minutes: 80 - depends_on: - - image-build-amd - -- label: Entrypoints Integration (API Server openai - Part 2) - key: entrypoints-integration-api-server-openai-part-2 - timeout_in_minutes: 50 - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - 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: mi300_1 - timeout_in_minutes: 60 - depends_on: - - image-build-amd - -- label: Entrypoints Integration (API Server openai - Part 3) - key: entrypoints-integration-api-server-openai-part-3 - timeout_in_minutes: 50 - device: h200_18gb - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/entrypoints/openai - - tests/entrypoints/test_chat_utils - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/test_multi_api_servers.py - mirror: - amd: - device: mi325_1 - timeout_in_minutes: 60 - depends_on: - - image-build-amd - -- label: Entrypoints Integration (API Server 2) +- label: Entrypoints Integration (API Server) + key: entrypoints-integration-api-server device: h200_35gb - key: entrypoints-integration-api-server-2 timeout_in_minutes: 130 working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -108,6 +50,75 @@ steps: depends_on: - image-build-amd +- label: Entrypoints Integration (API Server OpenAI - Part 1) + key: entrypoints-integration-api-server-openai-part-1 + timeout_in_minutes: 50 + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/entrypoints/openai + - tests/entrypoints/test_chat_utils + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/correctness + mirror: + amd: + device: mi300_1 + timeout_in_minutes: 80 + depends_on: + - image-build-amd + +- label: Entrypoints Integration (API Server OpenAI - Part 2) + key: entrypoints-integration-api-server-openai-part-2 + timeout_in_minutes: 50 + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/entrypoints/openai + - tests/entrypoints/test_chat_utils + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s entrypoints/openai/chat_completion + - pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py + mirror: + amd: + device: mi300_1 + timeout_in_minutes: 80 + depends_on: + - image-build-amd + +- label: Entrypoints Integration (API Server Generate) + key: entrypoints-integration-api-server-generate + timeout_in_minutes: 50 + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/tool_use + - tests/entrypoints/tool_parsers + - tests/entrypoints/anthropic + - tests/entrypoints/generate + commands: + - pytest -v -s tool_use + - pytest -v -s entrypoints/tool_parsers + - pytest -v -s entrypoints/generate + - pytest -v -s entrypoints/anthropic + mirror: + amd: + device: mi300_1 + timeout_in_minutes: 60 + depends_on: + - image-build-amd + +- label: Entrypoints Integration (Responses API) + key: entrypoints-integration-responses-api + timeout_in_minutes: 50 + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/entrypoints/openai/responses + commands: + - pytest -v -s entrypoints/openai/responses + - label: Entrypoints Integration (Speech to Text) device: h200_35gb key: entrypoints-integration-speech_to_text @@ -143,16 +154,6 @@ steps: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s entrypoints/pooling -- label: Entrypoints Integration (Responses API) - key: entrypoints-integration-responses-api - timeout_in_minutes: 50 - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/entrypoints/openai/responses - commands: - - pytest -v -s entrypoints/openai/responses - - label: OpenAI API Correctness key: openai-api-correctness timeout_in_minutes: 30 @@ -170,7 +171,6 @@ steps: source_file_dependencies: - csrc/ - vllm/entrypoints/openai/ - - vllm/model_executor/models/whisper.py - vllm/model_executor/layers/ - vllm/v1/attention/backends/ - vllm/v1/attention/selector.py diff --git a/.buildkite/test_areas/plugins.yaml b/.buildkite/test_areas/plugins.yaml index 0d23180f3e..591afd946d 100644 --- a/.buildkite/test_areas/plugins.yaml +++ b/.buildkite/test_areas/plugins.yaml @@ -37,6 +37,6 @@ steps: - pytest -v -s plugins_tests/test_scheduler_plugins.py - pip install -e ./plugins/vllm_add_dummy_model - pytest -v -s distributed/test_distributed_oot.py - - pytest -v -s entrypoints/openai/chat_completion/test_oot_registration.py # it needs a clean process - - pytest -v -s models/test_oot_registration.py # it needs a clean process - - pytest -v -s plugins/lora_resolvers # unit tests for in-tree lora resolver plugins + - pytest -v -s plugins_tests/test_oot_registration_online.py # it needs a clean process + - pytest -v -s plugins_tests/test_oot_registration_offline.py # it needs a clean process + - pytest -v -s plugins_tests/lora_resolvers # unit tests for in-tree lora resolver plugins diff --git a/tests/distributed/test_distributed_oot.py b/tests/distributed/test_distributed_oot.py index 9bd7603e73..5f7f3ffa8a 100644 --- a/tests/distributed/test_distributed_oot.py +++ b/tests/distributed/test_distributed_oot.py @@ -1,7 +1,7 @@ # SPDX-License-Identifier: Apache-2.0 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project -from tests.entrypoints.openai.chat_completion.test_oot_registration import ( +from tests.plugins_tests.test_oot_registration_online import ( run_and_test_dummy_opt_api_server, ) diff --git a/tests/entrypoints/openai/tool_parsers/__init__.py b/tests/entrypoints/tool_parsers/__init__.py similarity index 100% rename from tests/entrypoints/openai/tool_parsers/__init__.py rename to tests/entrypoints/tool_parsers/__init__.py diff --git a/tests/entrypoints/openai/tool_parsers/test_granite4_tool_parser.py b/tests/entrypoints/tool_parsers/test_granite4_tool_parser.py similarity index 99% rename from tests/entrypoints/openai/tool_parsers/test_granite4_tool_parser.py rename to tests/entrypoints/tool_parsers/test_granite4_tool_parser.py index 0397613c09..71fe7637bf 100644 --- a/tests/entrypoints/openai/tool_parsers/test_granite4_tool_parser.py +++ b/tests/entrypoints/tool_parsers/test_granite4_tool_parser.py @@ -5,7 +5,7 @@ import json import openai import pytest -from ....utils import RemoteOpenAIServer +from tests.utils import RemoteOpenAIServer MODEL = "ibm-granite/granite-4.0-h-tiny" diff --git a/tests/entrypoints/openai/tool_parsers/test_hermes_tool_parser.py b/tests/entrypoints/tool_parsers/test_hermes_tool_parser.py similarity index 99% rename from tests/entrypoints/openai/tool_parsers/test_hermes_tool_parser.py rename to tests/entrypoints/tool_parsers/test_hermes_tool_parser.py index 9ef9883009..5d769c0fd8 100644 --- a/tests/entrypoints/openai/tool_parsers/test_hermes_tool_parser.py +++ b/tests/entrypoints/tool_parsers/test_hermes_tool_parser.py @@ -9,12 +9,11 @@ import pytest_asyncio from huggingface_hub import snapshot_download from typing_extensions import TypedDict +from tests.utils import RemoteOpenAIServer from vllm.tool_parsers.abstract_tool_parser import ToolParser from vllm.tool_parsers.granite4_tool_parser import Granite4ToolParser from vllm.tool_parsers.hermes_tool_parser import Hermes2ProToolParser -from ....utils import RemoteOpenAIServer - LORA_MODEL = "minpeter/LoRA-Llama-3.2-1B-tool-vllm-ci" TOOLS = [ diff --git a/tests/entrypoints/openai/tool_parsers/test_openai_tool_parser.py b/tests/entrypoints/tool_parsers/test_openai_tool_parser.py similarity index 99% rename from tests/entrypoints/openai/tool_parsers/test_openai_tool_parser.py rename to tests/entrypoints/tool_parsers/test_openai_tool_parser.py index cedec72fe4..d99b66d9ac 100644 --- a/tests/entrypoints/openai/tool_parsers/test_openai_tool_parser.py +++ b/tests/entrypoints/tool_parsers/test_openai_tool_parser.py @@ -9,7 +9,7 @@ import pytest import pytest_asyncio from rapidfuzz import fuzz -from ....utils import RemoteOpenAIServer +from tests.utils import RemoteOpenAIServer MODEL_NAME = "openai/gpt-oss-20b" diff --git a/tests/plugins/lora_resolvers/__init__.py b/tests/entrypoints/unit_tests/__init__.py similarity index 100% rename from tests/plugins/lora_resolvers/__init__.py rename to tests/entrypoints/unit_tests/__init__.py diff --git a/tests/entrypoints/test_api_server_process_manager.py b/tests/entrypoints/unit_tests/test_api_server_process_manager.py similarity index 100% rename from tests/entrypoints/test_api_server_process_manager.py rename to tests/entrypoints/unit_tests/test_api_server_process_manager.py diff --git a/tests/entrypoints/test_chat_utils.py b/tests/entrypoints/unit_tests/test_chat_utils.py similarity index 100% rename from tests/entrypoints/test_chat_utils.py rename to tests/entrypoints/unit_tests/test_chat_utils.py diff --git a/tests/entrypoints/test_context.py b/tests/entrypoints/unit_tests/test_context.py similarity index 100% rename from tests/entrypoints/test_context.py rename to tests/entrypoints/unit_tests/test_context.py diff --git a/tests/entrypoints/test_grpc_health.py b/tests/entrypoints/unit_tests/test_grpc_health.py similarity index 100% rename from tests/entrypoints/test_grpc_health.py rename to tests/entrypoints/unit_tests/test_grpc_health.py diff --git a/tests/entrypoints/test_launch_cli.py b/tests/entrypoints/unit_tests/test_launch_cli.py similarity index 100% rename from tests/entrypoints/test_launch_cli.py rename to tests/entrypoints/unit_tests/test_launch_cli.py diff --git a/tests/plugins_tests/__init__.py b/tests/plugins_tests/__init__.py new file mode 100644 index 0000000000..e69de29bb2 diff --git a/tests/plugins_tests/lora_resolvers/__init__.py b/tests/plugins_tests/lora_resolvers/__init__.py new file mode 100644 index 0000000000..e69de29bb2 diff --git a/tests/plugins/lora_resolvers/test_filesystem_resolver.py b/tests/plugins_tests/lora_resolvers/test_filesystem_resolver.py similarity index 100% rename from tests/plugins/lora_resolvers/test_filesystem_resolver.py rename to tests/plugins_tests/lora_resolvers/test_filesystem_resolver.py diff --git a/tests/plugins/lora_resolvers/test_hf_hub_resolver.py b/tests/plugins_tests/lora_resolvers/test_hf_hub_resolver.py similarity index 100% rename from tests/plugins/lora_resolvers/test_hf_hub_resolver.py rename to tests/plugins_tests/lora_resolvers/test_hf_hub_resolver.py diff --git a/tests/models/test_oot_registration.py b/tests/plugins_tests/test_oot_registration_offline.py similarity index 98% rename from tests/models/test_oot_registration.py rename to tests/plugins_tests/test_oot_registration_offline.py index 15e94eef4a..3f483a5706 100644 --- a/tests/models/test_oot_registration.py +++ b/tests/plugins_tests/test_oot_registration_offline.py @@ -3,12 +3,11 @@ import pytest +from tests.utils import create_new_process_for_each_test from vllm import LLM, SamplingParams from vllm.assets.image import ImageAsset from vllm.multimodal.image import convert_image_mode -from ..utils import create_new_process_for_each_test - @create_new_process_for_each_test() def test_plugin( diff --git a/tests/entrypoints/openai/chat_completion/test_oot_registration.py b/tests/plugins_tests/test_oot_registration_online.py similarity index 100% rename from tests/entrypoints/openai/chat_completion/test_oot_registration.py rename to tests/plugins_tests/test_oot_registration_online.py