xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-11 01:55:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

Removing amdproduction Tests (#22027)

Browse Source 
Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com>
This commit is contained in:
Alexei-V-Ivanov-AMD 2025-07-31 11:53:27 -05:00 committed by GitHub
parent 58bb902186
commit 0780bb5783
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 23 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
.buildkite/test-pipeline.yaml
View File

@ -82,7 +82,7 @@ steps:
- bash standalone_tests/python_only_compile.sh - bash standalone_tests/python_only_compile.sh
- label: Basic Correctness Test # 30min - label: Basic Correctness Test # 30min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
fast_check: true fast_check: true
torch_nightly: true torch_nightly: true
source_file_dependencies: source_file_dependencies:
@ -99,7 +99,7 @@ steps:
- VLLM_TEST_ENABLE_ARTIFICIAL_PREEMPT=1 pytest -v -s basic_correctness/test_preemption.py - VLLM_TEST_ENABLE_ARTIFICIAL_PREEMPT=1 pytest -v -s basic_correctness/test_preemption.py
- label: Chunked Prefill Test - label: Chunked Prefill Test
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
- tests/basic_correctness/test_chunked_prefill - tests/basic_correctness/test_chunked_prefill
@ -108,7 +108,7 @@ steps:
- VLLM_ATTENTION_BACKEND=FLASH_ATTN pytest -v -s basic_correctness/test_chunked_prefill.py - VLLM_ATTENTION_BACKEND=FLASH_ATTN pytest -v -s basic_correctness/test_chunked_prefill.py
- label: Core Test # 10min - label: Core Test # 10min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
fast_check: true fast_check: true
source_file_dependencies: source_file_dependencies:
- vllm/core - vllm/core
@ -209,7 +209,7 @@ steps:
- pytest -v -s distributed/test_eplb_execute.py - pytest -v -s distributed/test_eplb_execute.py
- label: Metrics, Tracing Test # 10min - label: Metrics, Tracing Test # 10min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
num_gpus: 2 num_gpus: 2
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
@ -228,7 +228,7 @@ steps:
##### 1 GPU test ##### ##### 1 GPU test #####
- label: Regression Test # 5min - label: Regression Test # 5min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
- tests/test_regression - tests/test_regression
@ -280,7 +280,7 @@ steps:
- pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine
- label: Examples Test # 25min - label: Examples Test # 25min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
working_dir: "/vllm-workspace/examples" working_dir: "/vllm-workspace/examples"
source_file_dependencies: source_file_dependencies:
- vllm/entrypoints - vllm/entrypoints
@ -305,7 +305,7 @@ steps:
- VLLM_USE_V1=0 python3 offline_inference/profiling.py --model facebook/opt-125m run_num_steps --num-steps 2 - VLLM_USE_V1=0 python3 offline_inference/profiling.py --model facebook/opt-125m run_num_steps --num-steps 2
- label: Prefix Caching Test # 9min - label: Prefix Caching Test # 9min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
- tests/prefix_caching - tests/prefix_caching
@ -314,7 +314,7 @@ steps:
- label: Platform Tests (CUDA) - label: Platform Tests (CUDA)
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
- tests/cuda - tests/cuda
@ -355,7 +355,7 @@ steps:
- pytest -v -s compile/test_async_tp.py - pytest -v -s compile/test_async_tp.py
- label: PyTorch Fullgraph Smoke Test # 9min - label: PyTorch Fullgraph Smoke Test # 9min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
torch_nightly: true torch_nightly: true
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
@ -368,7 +368,7 @@ steps:
- pytest -v -s compile/piecewise/test_full_cudagraph.py - pytest -v -s compile/piecewise/test_full_cudagraph.py
- label: PyTorch Fullgraph Test # 18min - label: PyTorch Fullgraph Test # 18min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
torch_nightly: true torch_nightly: true
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
@ -377,7 +377,7 @@ steps:
- pytest -v -s compile/test_full_graph.py - pytest -v -s compile/test_full_graph.py
- label: Kernels Core Operation Test - label: Kernels Core Operation Test
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
source_file_dependencies: source_file_dependencies:
- csrc/ - csrc/
- tests/kernels/core - tests/kernels/core
@ -416,7 +416,7 @@ steps:
parallelism: 2 parallelism: 2
- label: Kernels Mamba Test - label: Kernels Mamba Test
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
source_file_dependencies: source_file_dependencies:
- csrc/mamba/ - csrc/mamba/
- tests/kernels/mamba - tests/kernels/mamba
@ -424,7 +424,7 @@ steps:
- pytest -v -s kernels/mamba - pytest -v -s kernels/mamba
- label: Tensorizer Test # 11min - label: Tensorizer Test # 11min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
soft_fail: true soft_fail: true
source_file_dependencies: source_file_dependencies:
- vllm/model_executor/model_loader - vllm/model_executor/model_loader
@ -437,7 +437,7 @@ steps:
- pytest -v -s entrypoints/openai/test_tensorizer_entrypoint.py - pytest -v -s entrypoints/openai/test_tensorizer_entrypoint.py
- label: Model Executor Test - label: Model Executor Test
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
source_file_dependencies: source_file_dependencies:
- vllm/model_executor - vllm/model_executor
- tests/model_executor - tests/model_executor
@ -447,7 +447,7 @@ steps:
- pytest -v -s model_executor - pytest -v -s model_executor
- label: Benchmarks # 9min - label: Benchmarks # 9min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
working_dir: "/vllm-workspace/.buildkite" working_dir: "/vllm-workspace/.buildkite"
source_file_dependencies: source_file_dependencies:
- benchmarks/ - benchmarks/
@ -455,7 +455,7 @@ steps:
- bash scripts/run-benchmarks.sh - bash scripts/run-benchmarks.sh
- label: Benchmarks CLI Test # 10min - label: Benchmarks CLI Test # 10min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
- tests/benchmarks/ - tests/benchmarks/
@ -494,7 +494,7 @@ steps:
- pytest -s entrypoints/openai/correctness/ - pytest -s entrypoints/openai/correctness/
- label: Encoder Decoder tests # 5min - label: Encoder Decoder tests # 5min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
- tests/encoder_decoder - tests/encoder_decoder
@ -502,7 +502,7 @@ steps:
- pytest -v -s encoder_decoder - pytest -v -s encoder_decoder
- label: OpenAI-Compatible Tool Use # 20 min - label: OpenAI-Compatible Tool Use # 20 min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
fast_check: false fast_check: false
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
@ -623,7 +623,7 @@ steps:
# This test is used only in PR development phase to test individual models and should never run on main # This test is used only in PR development phase to test individual models and should never run on main
- label: Custom Models Test - label: Custom Models Test
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
optional: true optional: true
commands: commands:
- echo 'Testing custom models...' - echo 'Testing custom models...'
@ -658,7 +658,7 @@ steps:
##### multi gpus test ##### ##### multi gpus test #####
- label: Distributed Comm Ops Test # 7min - label: Distributed Comm Ops Test # 7min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
working_dir: "/vllm-workspace/tests" working_dir: "/vllm-workspace/tests"
num_gpus: 2 num_gpus: 2
source_file_dependencies: source_file_dependencies:
@ -755,7 +755,7 @@ steps:
- pytest -v -s plugins/lora_resolvers # unit tests for in-tree lora resolver plugins - pytest -v -s plugins/lora_resolvers # unit tests for in-tree lora resolver plugins
- label: Multi-step Tests (4 GPUs) # 36min - label: Multi-step Tests (4 GPUs) # 36min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
working_dir: "/vllm-workspace/tests" working_dir: "/vllm-workspace/tests"
num_gpus: 4 num_gpus: 4
source_file_dependencies: source_file_dependencies:
@ -776,7 +776,7 @@ steps:
- pytest -v -s multi_step/test_correctness_llm.py - pytest -v -s multi_step/test_correctness_llm.py
- label: Pipeline Parallelism Test # 45min - label: Pipeline Parallelism Test # 45min
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
working_dir: "/vllm-workspace/tests" working_dir: "/vllm-workspace/tests"
num_gpus: 4 num_gpus: 4
source_file_dependencies: source_file_dependencies:
@ -790,7 +790,7 @@ steps:
- pytest -v -s distributed/test_pipeline_parallel.py - pytest -v -s distributed/test_pipeline_parallel.py
- label: LoRA TP Test (Distributed) - label: LoRA TP Test (Distributed)
mirror_hardwares: [amdexperimental, amdproduction] mirror_hardwares: [amdexperimental]
num_gpus: 4 num_gpus: 4
source_file_dependencies: source_file_dependencies:
- vllm/lora - vllm/lora