iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[ROCm][CI] Set all timeout_in_minutes to 180 (#48146)

Browse Source 
Signed-off-by: charlifu <charlifu@amd.com>
This commit is contained in:
Charlie Fu
2026-07-09 17:52:26 +00:00
committed by GitHub
parent 429f405748
commit 67e7ea8977
1 changed files with 27 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.buildkite/test-amd.yaml
+27 -27
View File
@@ -275,7 +275,7 @@ steps:
- pytest -v -s v1/cudagraph/test_cudagraph_mode.py
- label: e2e Core (1 GPU) # TBD
timeout_in_minutes: 35
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx90anightly, amdmi250]
agent_pool: mi250_1
optional: true
@@ -439,7 +439,7 @@ steps:
#----------------------------------------------------------- mi250 · docker ----------------------------------------------------------#
- label: Docker Build Metadata (ROCm) # TBD
timeout_in_minutes: 20
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx90anightly, amdmi250]
agent_pool: mi250_1
no_gpu: true
@@ -467,7 +467,7 @@ steps:
#----------------------------------------------------- mi300 · basic_correctness -----------------------------------------------------#
- label: Basic Correctness # TBD
timeout_in_minutes: 95
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_1
fast_check: true
@@ -484,7 +484,7 @@ steps:
- pytest -v -s basic_correctness/test_cpu_offload.py
- label: Distributed Model Tests (2 GPUs) # TBD
timeout_in_minutes: 110
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_2
num_gpus: 2
@@ -724,7 +724,7 @@ steps:
- pytest -v -s distributed/test_eplb_spec_decode.py
- label: Distributed Tests (2xH100-2xMI300) # TBD
timeout_in_minutes: 75
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_2
num_gpus: 2
@@ -1297,7 +1297,7 @@ steps:
#--------------------------------------------------------- mi300 · examples ----------------------------------------------------------#
- label: Examples # TBD
timeout_in_minutes: 90
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_1
optional: true
@@ -1348,7 +1348,7 @@ steps:
- pytest -v -s tests/kernels/ir
- label: Kernels Attention Test %N # TBD
timeout_in_minutes: 100
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_1
optional: true
@@ -1397,7 +1397,7 @@ steps:
- pytest -v -s kernels/test_kda.py
- label: Kernels MoE Test %N # TBD
timeout_in_minutes: 95
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_1
optional: true
@@ -1511,7 +1511,7 @@ steps:
#---------------------------------------------------- mi300 · model_runner_v2 -------------------------------------------------------#
- label: Model Runner V2 Core Tests # TBD
timeout_in_minutes: 60
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_1
optional: true
@@ -1535,7 +1535,7 @@ steps:
- pytest -v -s entrypoints/llm/test_struct_output_generate.py -k "xgrammar and not speculative_config6 and not speculative_config7 and not speculative_config8 and not speculative_config0"
- label: Model Runner V2 Examples # TBD
timeout_in_minutes: 60
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_1
optional: true
@@ -1569,7 +1569,7 @@ steps:
- python3 features/speculative_decoding/spec_decode_offline.py --test --method eagle3 --num_spec_tokens 3 --dataset-name hf --dataset-path philschmid/mt-bench --num-prompts 80 --temp 0 --top-p 1.0 --top-k -1 --tp 1 --enable-chunked-prefill --max-model-len 1536
- label: Model Runner V2 Distributed (2 GPUs) # TBD
timeout_in_minutes: 60
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_2
num_gpus: 2
@@ -1661,7 +1661,7 @@ steps:
- pytest -v -s models/test_initialization.py::test_can_initialize_small_subset
- label: Basic Models Tests (Other) # TBD
timeout_in_minutes: 90
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_1
optional: true
@@ -1806,7 +1806,7 @@ steps:
- cd .. && VLLM_WORKER_MULTIPROC_METHOD=spawn pytest -v -s tests/models/multimodal/generation/test_whisper.py -m core_model
- label: Multi-Modal Processor # 1h 42m
timeout_in_minutes: 138
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_1
optional: true
@@ -2255,7 +2255,7 @@ steps:
- pytest -v -s v1/e2e/spec_decode -k "draft_model or no_sync or batch_inference"
- label: Spec Decode Eagle # TBD
timeout_in_minutes: 90
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_1
optional: true
@@ -2472,7 +2472,7 @@ steps:
- DP_SIZE=2 pytest -v -s entrypoints/openai/test_multi_api_servers.py
- label: Metrics, Tracing (2 GPUs) # TBD
timeout_in_minutes: 65
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_2
optional: true
@@ -2678,7 +2678,7 @@ steps:
#------------------------------------------------------ mi300 · weight_loading -------------------------------------------------------#
- label: Weight Loading Multiple GPU # TBD
timeout_in_minutes: 75
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_2
num_gpus: 2
@@ -2690,7 +2690,7 @@ steps:
- bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-amd.txt
- label: Weight Loading Multiple GPU - Large Models # TBD
timeout_in_minutes: 75
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
agent_pool: mi300_2
num_gpus: 2
@@ -3089,7 +3089,7 @@ steps:
- pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-gfx950.txt
- label: LM Eval Qwen3-5 Models (B200-MI355) # TBD
timeout_in_minutes: 120
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
agent_pool: mi355_2
num_gpus: 2
@@ -3171,7 +3171,7 @@ steps:
#--------------------------------------------------------- mi355 · examples ----------------------------------------------------------#
- label: Examples # TBD
timeout_in_minutes: 100
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
agent_pool: mi355_1
working_dir: "/vllm-workspace/examples"
@@ -3206,7 +3206,7 @@ steps:
#---------------------------------------------------------- mi355 · kernels ----------------------------------------------------------#
- label: Kernels (B200-MI355) # TBD
timeout_in_minutes: 15
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
agent_pool: mi355_1
working_dir: "/vllm-workspace/"
@@ -3231,7 +3231,7 @@ steps:
- pytest -v -s tests/kernels/attention/test_rocm_aiter_mla_decode_metadata.py
- label: Kernels Attention Test %N # TBD
timeout_in_minutes: 100
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
agent_pool: mi355_1
parallelism: 2
@@ -3248,7 +3248,7 @@ steps:
- pytest -v -s kernels/attention --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
- label: Kernels MoE Test %N # TBD
timeout_in_minutes: 50
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
agent_pool: mi355_1
parallelism: 5
@@ -3512,7 +3512,7 @@ steps:
- pytest -v -s v1/attention
- label: V1 Core + KV + Metrics # TBD
timeout_in_minutes: 60
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
agent_pool: mi355_1
optional: true
@@ -3538,7 +3538,7 @@ steps:
- pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine
- label: V1 Sample + Logits # TBD
timeout_in_minutes: 60
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
agent_pool: mi355_1
optional: true
@@ -3558,7 +3558,7 @@ steps:
- pytest -v -s v1/test_outputs.py
- label: V1 Spec Decode # TBD
timeout_in_minutes: 60
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
agent_pool: mi355_1
working_dir: "/vllm-workspace/tests"
@@ -3571,7 +3571,7 @@ steps:
#------------------------------------------------------ mi355 · weight_loading -------------------------------------------------------#
- label: Weight Loading Multiple GPU # TBD
timeout_in_minutes: 75
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
agent_pool: mi355_2
num_gpus: 2
@@ -3583,7 +3583,7 @@ steps:
- bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-amd.txt
- label: Weight Loading Multiple GPU - Large Models # TBD
timeout_in_minutes: 75
timeout_in_minutes: 180
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
agent_pool: mi355_2
working_dir: "/vllm-workspace/tests"