[CI][ROCm] Standardize AMD test job labels by device (#52976)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com> Signed-off-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
+376
-332
File diff suppressed because it is too large
Load Diff
@@ -31,14 +31,14 @@ steps:
|
|||||||
- vllm/v1/engine/
|
- vllm/v1/engine/
|
||||||
- vllm/v1/worker/
|
- vllm/v1/worker/
|
||||||
- tests/v1/distributed
|
- tests/v1/distributed
|
||||||
- tests/entrypoints/openai/test_multi_api_servers.py
|
- tests/entrypoints/launchers/api_server/test_multi_api_servers.py
|
||||||
commands:
|
commands:
|
||||||
# https://github.com/NVIDIA/nccl/issues/1838
|
# https://github.com/NVIDIA/nccl/issues/1838
|
||||||
- export NCCL_CUMEM_HOST_ENABLE=0
|
- export NCCL_CUMEM_HOST_ENABLE=0
|
||||||
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_async_llm_dp.py
|
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_async_llm_dp.py
|
||||||
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_eagle_dp.py
|
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_eagle_dp.py
|
||||||
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_external_lb_dp.py
|
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_external_lb_dp.py
|
||||||
- DP_SIZE=2 pytest -v -s entrypoints/openai/test_multi_api_servers.py
|
- DP_SIZE=2 pytest -v -s entrypoints/launchers/api_server/test_multi_api_servers.py
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) Distributed DP Basic"
|
label: ":amd: (MI300) Distributed DP Basic"
|
||||||
@@ -56,7 +56,7 @@ steps:
|
|||||||
- vllm/v1/engine/
|
- vllm/v1/engine/
|
||||||
- vllm/v1/worker/
|
- vllm/v1/worker/
|
||||||
- tests/v1/distributed
|
- tests/v1/distributed
|
||||||
- tests/entrypoints/openai/test_multi_api_servers.py
|
- tests/entrypoints/launchers/api_server/test_multi_api_servers.py
|
||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
|
|
||||||
- label: ":nvidia: (L4) Distributed Compile + RPC"
|
- label: ":nvidia: (L4) Distributed Compile + RPC"
|
||||||
|
|||||||
@@ -80,7 +80,7 @@ steps:
|
|||||||
label: ":amd: (MI300) Multimodal Models (Standard) 4: other + whisper"
|
label: ":amd: (MI300) Multimodal Models (Standard) 4: other + whisper"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi300_1
|
||||||
timeout_in_minutes: 50
|
timeout_in_minutes: 70
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
|
|
||||||
|
|||||||
@@ -102,7 +102,7 @@ def run_dp_sharded_vision_model_vs_direct(
|
|||||||
# Set random seed for reproducibility
|
# Set random seed for reproducibility
|
||||||
set_random_seed(0)
|
set_random_seed(0)
|
||||||
|
|
||||||
device = f"{current_platform.device_name}:{local_rank}"
|
device = f"{current_platform.device_type}:{local_rank}"
|
||||||
torch.accelerator.set_device_index(device)
|
torch.accelerator.set_device_index(device)
|
||||||
torch.set_default_device(device)
|
torch.set_default_device(device)
|
||||||
|
|
||||||
@@ -288,7 +288,7 @@ def run_dp_sharded_mrope_vision_model_vs_direct(
|
|||||||
"""
|
"""
|
||||||
# Set random seed for reproducibility
|
# Set random seed for reproducibility
|
||||||
set_random_seed(0)
|
set_random_seed(0)
|
||||||
device = f"{current_platform.device_name}:{local_rank}"
|
device = f"{current_platform.device_type}:{local_rank}"
|
||||||
torch.accelerator.set_device_index(device)
|
torch.accelerator.set_device_index(device)
|
||||||
torch.set_default_device(device)
|
torch.set_default_device(device)
|
||||||
|
|
||||||
@@ -365,7 +365,7 @@ def run_dp_sharded_mrope_vision_model_empty_input_worker(
|
|||||||
):
|
):
|
||||||
"""Test run_dp_sharded_mrope_vision_model with empty input."""
|
"""Test run_dp_sharded_mrope_vision_model with empty input."""
|
||||||
# Set up distributed environment
|
# Set up distributed environment
|
||||||
device = f"{current_platform.device_name}:{local_rank}"
|
device = f"{current_platform.device_type}:{local_rank}"
|
||||||
torch.accelerator.set_device_index(device)
|
torch.accelerator.set_device_index(device)
|
||||||
torch.set_default_device(device)
|
torch.set_default_device(device)
|
||||||
|
|
||||||
@@ -414,7 +414,7 @@ def run_dp_sharded_mrope_vision_model_uneven_load_worker(
|
|||||||
"""Test run_dp_sharded_mrope_vision_model with uneven load distribution."""
|
"""Test run_dp_sharded_mrope_vision_model with uneven load distribution."""
|
||||||
# Set up distributed environment
|
# Set up distributed environment
|
||||||
set_random_seed(123)
|
set_random_seed(123)
|
||||||
device = f"{current_platform.device_name}:{local_rank}"
|
device = f"{current_platform.device_type}:{local_rank}"
|
||||||
torch.accelerator.set_device_index(device)
|
torch.accelerator.set_device_index(device)
|
||||||
torch.set_default_device(device)
|
torch.set_default_device(device)
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user