[CI] Add Blackwell AsyncTP correctness test (#35871)
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
This commit is contained in:
@@ -36,6 +36,16 @@ steps:
|
|||||||
- export VLLM_TEST_CLEAN_GPU_MEMORY=1
|
- export VLLM_TEST_CLEAN_GPU_MEMORY=1
|
||||||
- pytest -v -s tests/compile/correctness_e2e/test_async_tp.py
|
- pytest -v -s tests/compile/correctness_e2e/test_async_tp.py
|
||||||
|
|
||||||
|
- label: AsyncTP Correctness Tests (B200)
|
||||||
|
timeout_in_minutes: 50
|
||||||
|
working_dir: "/vllm-workspace/"
|
||||||
|
device: b200
|
||||||
|
optional: true
|
||||||
|
num_devices: 2
|
||||||
|
commands:
|
||||||
|
- export VLLM_TEST_CLEAN_GPU_MEMORY=1
|
||||||
|
- pytest -v -s tests/compile/correctness_e2e/test_async_tp.py
|
||||||
|
|
||||||
- label: Distributed Compile Unit Tests (2xH100)
|
- label: Distributed Compile Unit Tests (2xH100)
|
||||||
timeout_in_minutes: 20
|
timeout_in_minutes: 20
|
||||||
working_dir: "/vllm-workspace/"
|
working_dir: "/vllm-workspace/"
|
||||||
|
|||||||
@@ -31,7 +31,12 @@ def test_async_tp_pass_correctness(
|
|||||||
distributed_backend: str,
|
distributed_backend: str,
|
||||||
eager_mode: bool,
|
eager_mode: bool,
|
||||||
num_gpus_available: int,
|
num_gpus_available: int,
|
||||||
|
monkeypatch,
|
||||||
):
|
):
|
||||||
|
# Disable FlashInfer FP8 scaled_mm kernel as it is incompatible with
|
||||||
|
# async TP patterns. No-op on H100 (kernel requires CC >= 100).
|
||||||
|
monkeypatch.setenv("VLLM_DISABLED_KERNELS", "FlashInferFP8ScaledMMLinearKernel")
|
||||||
|
|
||||||
model_info = HF_EXAMPLE_MODELS.find_hf_info(model_id)
|
model_info = HF_EXAMPLE_MODELS.find_hf_info(model_id)
|
||||||
model_info.check_transformers_version(on_fail="skip")
|
model_info.check_transformers_version(on_fail="skip")
|
||||||
model_info.check_available_online(on_fail="skip")
|
model_info.check_available_online(on_fail="skip")
|
||||||
|
|||||||
Reference in New Issue
Block a user