Removing amdproduction Tests (#22027)

Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com>

.buildkite/test-pipeline.yaml

@@ -82,7 +82,7 @@ steps:
   - bash standalone_tests/python_only_compile.sh
 
 - label: Basic Correctness Test # 30min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   fast_check: true
   torch_nightly: true
   source_file_dependencies:
@@ -99,7 +99,7 @@ steps:
   - VLLM_TEST_ENABLE_ARTIFICIAL_PREEMPT=1 pytest -v -s basic_correctness/test_preemption.py
 
 - label: Chunked Prefill Test
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   source_file_dependencies:
   - vllm/
   - 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
 
 - label: Core Test # 10min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   fast_check: true
   source_file_dependencies:
   - vllm/core
@@ -209,7 +209,7 @@ steps:
   - pytest -v -s distributed/test_eplb_execute.py
 
 - label: Metrics, Tracing Test # 10min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   num_gpus: 2
   source_file_dependencies:
   - vllm/
@@ -228,7 +228,7 @@ steps:
 #####  1 GPU test  #####
 
 - label: Regression Test # 5min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   source_file_dependencies:
   - vllm/
   - tests/test_regression
@@ -280,7 +280,7 @@ steps:
     - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine
 
 - label: Examples Test # 25min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   working_dir: "/vllm-workspace/examples"
   source_file_dependencies:
   - 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
 
 - label: Prefix Caching Test # 9min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   source_file_dependencies:
   - vllm/
   - tests/prefix_caching
@@ -314,7 +314,7 @@ steps:
 
 
 - label: Platform Tests (CUDA)
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   source_file_dependencies:
   - vllm/
   - tests/cuda
@@ -355,7 +355,7 @@ steps:
     - pytest -v -s compile/test_async_tp.py
 
 - label: PyTorch Fullgraph Smoke Test # 9min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   torch_nightly: true
   source_file_dependencies:
   - vllm/
@@ -368,7 +368,7 @@ steps:
   - pytest -v -s compile/piecewise/test_full_cudagraph.py
 
 - label: PyTorch Fullgraph Test # 18min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   torch_nightly: true
   source_file_dependencies:
   - vllm/
@@ -377,7 +377,7 @@ steps:
   - pytest -v -s compile/test_full_graph.py
 
 - label: Kernels Core Operation Test
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   source_file_dependencies:
   - csrc/
   - tests/kernels/core
@@ -416,7 +416,7 @@ steps:
   parallelism: 2
 
 - label: Kernels Mamba Test
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   source_file_dependencies:
   - csrc/mamba/
   - tests/kernels/mamba
@@ -424,7 +424,7 @@ steps:
     - pytest -v -s kernels/mamba
 
 - label: Tensorizer Test # 11min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   soft_fail: true
   source_file_dependencies:
   - vllm/model_executor/model_loader
@@ -437,7 +437,7 @@ steps:
     - pytest -v -s entrypoints/openai/test_tensorizer_entrypoint.py
 
 - label: Model Executor Test
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   source_file_dependencies:
   - vllm/model_executor
   - tests/model_executor
@@ -447,7 +447,7 @@ steps:
     - pytest -v -s model_executor
 
 - label: Benchmarks # 9min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   working_dir: "/vllm-workspace/.buildkite"
   source_file_dependencies:
   - benchmarks/
@@ -455,7 +455,7 @@ steps:
   - bash scripts/run-benchmarks.sh
 
 - label: Benchmarks CLI Test # 10min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   source_file_dependencies:
   - vllm/
   - tests/benchmarks/
@@ -494,7 +494,7 @@ steps:
   - pytest -s entrypoints/openai/correctness/
 
 - label: Encoder Decoder tests # 5min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   source_file_dependencies:
   - vllm/
   - tests/encoder_decoder
@@ -502,7 +502,7 @@ steps:
     - pytest -v -s encoder_decoder
 
 - label: OpenAI-Compatible Tool Use # 20 min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   fast_check: false
   source_file_dependencies:
     - 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
 - label: Custom Models Test
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   optional: true
   commands:
     - echo 'Testing custom models...'
@@ -658,7 +658,7 @@ steps:
 #####  multi gpus test  #####
 
 - label: Distributed Comm Ops Test # 7min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   working_dir: "/vllm-workspace/tests"
   num_gpus: 2
   source_file_dependencies:
@@ -755,7 +755,7 @@ steps:
   - pytest -v -s plugins/lora_resolvers # unit tests for in-tree lora resolver plugins
 
 - label: Multi-step Tests (4 GPUs) # 36min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   working_dir: "/vllm-workspace/tests"
   num_gpus: 4
   source_file_dependencies:
@@ -776,7 +776,7 @@ steps:
   - pytest -v -s multi_step/test_correctness_llm.py
 
 - label: Pipeline Parallelism Test # 45min
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   working_dir: "/vllm-workspace/tests"
   num_gpus: 4
   source_file_dependencies:
@@ -790,7 +790,7 @@ steps:
   - pytest -v -s distributed/test_pipeline_parallel.py
 
 - label: LoRA TP Test (Distributed)
-  mirror_hardwares: [amdexperimental, amdproduction]
+  mirror_hardwares: [amdexperimental]
   num_gpus: 4
   source_file_dependencies:
   - vllm/lora