112 lines
4.6 KiB
YAML
112 lines
4.6 KiB
YAML
group: Rust Frontend E2E
|
|
depends_on:
|
|
- image-build
|
|
steps:
|
|
- label: Rust Frontend OpenAI Coverage
|
|
timeout_in_minutes: 90
|
|
device: h200_18gb
|
|
working_dir: "/vllm-workspace/tests"
|
|
source_file_dependencies:
|
|
- rust/
|
|
- vllm/benchmarks/
|
|
- vllm/entrypoints/openai/
|
|
- vllm/entrypoints/serve/
|
|
- vllm/v1/sample/
|
|
- tests/utils.py
|
|
- tests/benchmarks/test_serve_cli.py
|
|
- tests/entrypoints/openai/chat_completion/test_chat_completion.py
|
|
# - tests/entrypoints/openai/chat_completion/test_chat_logit_bias_validation.py
|
|
|
|
# - tests/entrypoints/openai/completion/test_prompt_validation.py
|
|
- tests/entrypoints/openai/completion/test_shutdown.py
|
|
# - tests/entrypoints/openai/test_return_token_ids.py
|
|
# - tests/entrypoints/openai/test_uds.py
|
|
- tests/v1/sample/test_logprobs_e2e.py
|
|
commands:
|
|
- export VLLM_USE_RUST_FRONTEND=1
|
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
- pytest -v -s benchmarks/test_serve_cli.py -k "not insecure and not (test_bench_serve and not test_bench_serve_chat)"
|
|
- pytest -v -s entrypoints/openai/chat_completion/test_chat_completion.py -k "not test_invalid_json_schema and not test_invalid_regex"
|
|
# - pytest -v -s entrypoints/openai/chat_completion/test_chat_logit_bias_validation.py -k "not invalid"
|
|
|
|
# - pytest -v -s entrypoints/openai/completion/test_prompt_validation.py -k "not prompt_embeds"
|
|
- pytest -v -s entrypoints/openai/completion/test_shutdown.py -k "not engine_failure and not test_abort_timeout_exits_quickly"
|
|
# - pytest -v -s entrypoints/openai/test_return_token_ids.py
|
|
# - pytest -v -s entrypoints/openai/test_uds.py
|
|
- pytest -v -s v1/sample/test_logprobs_e2e.py -k "test_prompt_logprobs_e2e_server"
|
|
|
|
- label: Rust Frontend Serve/Admin Coverage
|
|
timeout_in_minutes: 60
|
|
device: h200_18gb
|
|
working_dir: "/vllm-workspace/tests"
|
|
source_file_dependencies:
|
|
- rust/
|
|
- vllm/entrypoints/openai/
|
|
- vllm/entrypoints/serve/
|
|
- vllm/v1/engine/
|
|
- tests/utils.py
|
|
# - tests/entrypoints/serve/dev/rpc/test_collective_rpc.py
|
|
- 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
|
|
commands:
|
|
- export VLLM_USE_RUST_FRONTEND=1
|
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
# - 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/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
|
|
|
|
- label: Rust Frontend Core Correctness
|
|
timeout_in_minutes: 30
|
|
device: h200_18gb
|
|
working_dir: "/vllm-workspace/tests"
|
|
source_file_dependencies:
|
|
- rust/
|
|
- vllm/entrypoints/openai/
|
|
- tests/utils.py
|
|
- tests/entrypoints/openai/correctness/test_lmeval.py
|
|
commands:
|
|
- export VLLM_USE_RUST_FRONTEND=1
|
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
- pytest -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine
|
|
|
|
- label: Rust Frontend Tool Use
|
|
timeout_in_minutes: 60
|
|
working_dir: "/vllm-workspace/tests"
|
|
source_file_dependencies:
|
|
- rust/
|
|
- vllm/entrypoints/openai/
|
|
- vllm/tool_parsers/
|
|
- tests/utils.py
|
|
- tests/tool_use/
|
|
commands:
|
|
- export VLLM_USE_RUST_FRONTEND=1
|
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
- pytest -v -s tool_use --ignore=tool_use/mistral --models llama3.2 -k "not test_response_format_with_tool_choice_required and not test_parallel_tool_calls_false and not test_tool_call_and_choice"
|
|
|
|
- label: Rust Frontend Distributed
|
|
timeout_in_minutes: 30
|
|
num_devices: 4
|
|
working_dir: "/vllm-workspace/tests"
|
|
source_file_dependencies:
|
|
- rust/
|
|
- vllm/distributed/
|
|
- vllm/engine/
|
|
- vllm/executor/
|
|
- vllm/v1/engine/
|
|
- vllm/v1/worker/
|
|
- tests/utils.py
|
|
- tests/v1/distributed/test_external_lb_dp.py
|
|
- tests/v1/distributed/test_hybrid_lb_dp.py
|
|
- tests/v1/distributed/test_internal_lb_dp.py
|
|
commands:
|
|
- export VLLM_USE_RUST_FRONTEND=1
|
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
- export NCCL_CUMEM_HOST_ENABLE=0
|
|
- TP_SIZE=1 DP_SIZE=4 pytest -v -s v1/distributed/test_internal_lb_dp.py -k "not 4 and not server_info"
|
|
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_external_lb_dp.py -k "not 4 and not server_info"
|
|
- TP_SIZE=1 DP_SIZE=4 pytest -v -s v1/distributed/test_hybrid_lb_dp.py -k "not 4 and not server_info"
|