93 lines
2.7 KiB
YAML
93 lines
2.7 KiB
YAML
group: Basic Correctness
|
|
depends_on:
|
|
- image-build
|
|
steps:
|
|
- label: ":nvidia: (H200 MIG 18GB) Basic Correctness Models %N"
|
|
key: basic-correctness
|
|
timeout_in_minutes: 68
|
|
device: h200_18gb
|
|
parallelism: 2
|
|
source_file_dependencies: &basic-correctness-deps
|
|
- vllm/
|
|
- "!vllm/distributed/kv_transfer/"
|
|
- tests/basic_correctness/
|
|
commands:
|
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
- pytest -v -s basic_correctness/models --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
|
|
mirror:
|
|
amd:
|
|
label: ":amd: (MI355 DPX) Basic Correctness Models %N"
|
|
dind: false
|
|
device: mi355_dpx
|
|
timeout_in_minutes: 60
|
|
depends_on:
|
|
- image-build-amd
|
|
|
|
- label: ":nvidia: (H200 MIG 18GB) Basic Correctness CuMem"
|
|
key: basic-correctness-cumem
|
|
timeout_in_minutes: 68
|
|
device: h200_18gb
|
|
source_file_dependencies: *basic-correctness-deps
|
|
commands:
|
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
- pytest -v -s basic_correctness/memory/cumem
|
|
mirror:
|
|
amd:
|
|
label: ":amd: (MI355 DPX) Basic Correctness CuMem"
|
|
dind: false
|
|
device: mi355_dpx
|
|
timeout_in_minutes: 60
|
|
depends_on:
|
|
- image-build-amd
|
|
|
|
- label: ":nvidia: (H200 MIG 18GB) Basic Correctness Sleep Mode"
|
|
key: basic-correctness-sleep-mode
|
|
timeout_in_minutes: 68
|
|
device: h200_18gb
|
|
source_file_dependencies: *basic-correctness-deps
|
|
commands:
|
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
- pytest -v -s basic_correctness/memory/sleep_mode
|
|
mirror:
|
|
amd:
|
|
label: ":amd: (MI300) Basic Correctness Sleep Mode"
|
|
dind: false
|
|
device: mi300_1
|
|
timeout_in_minutes: 60
|
|
depends_on:
|
|
- image-build-amd
|
|
|
|
- label: ":nvidia: (H200 MIG 18GB) Basic Correctness CPU Offload"
|
|
key: basic-correctness-cpu-offload
|
|
timeout_in_minutes: 68
|
|
device: h200_18gb
|
|
source_file_dependencies: *basic-correctness-deps
|
|
commands:
|
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
- pytest -v -s basic_correctness/cpu_offload
|
|
mirror:
|
|
amd:
|
|
label: ":amd: (MI355 DPX) Basic Correctness CPU Offload"
|
|
dind: false
|
|
device: mi355_dpx
|
|
timeout_in_minutes: 60
|
|
depends_on:
|
|
- image-build-amd
|
|
|
|
- label: ":nvidia: (H200 MIG 18GB) Basic Correctness Prefetch Offload"
|
|
key: basic-correctness-prefetch-offload
|
|
timeout_in_minutes: 68
|
|
device: h200_18gb
|
|
source_file_dependencies: *basic-correctness-deps
|
|
commands:
|
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
- pytest -v -s basic_correctness/prefetch_offload
|
|
mirror:
|
|
amd:
|
|
label: ":amd: (MI355 DPX) Basic Correctness Prefetch Offload"
|
|
dind: false
|
|
device: mi355_dpx
|
|
timeout_in_minutes: 60
|
|
depends_on:
|
|
- image-build-amd
|