Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions qa/L2_jax_distributed_unittest/test.sh
Original file line number Diff line number Diff line change
Expand Up @@ -13,3 +13,6 @@ mkdir -p "$XML_LOG_DIR"

# Use --xla_gpu_enable_triton_gemm=false to ensure the reference JAX implementation we are using is accurate.
XLA_FLAGS="$XLA_FLAGS --xla_gpu_enable_triton_gemm=false" NVTE_JAX_UNITTEST_LEVEL="L2" python3 -m pytest -c $TE_PATH/tests/jax/pytest.ini -v --junitxml=$XML_LOG_DIR/pytest.xml $TE_PATH/tests/jax/test_distributed_*

# NCCL EP multi-process suite. The launcher skips when fewer than 4 GPUs or no NVLink is detected.
TE_PATH=$TE_PATH bash $TE_PATH/tests/jax/multi_process_launch_ep.sh
2 changes: 1 addition & 1 deletion qa/L2_jax_unittest/test.sh
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ pip3 install pytest==8.2.1 || error_exit "Failed to install pytest"
: ${XML_LOG_DIR:=/logs}
mkdir -p "$XML_LOG_DIR"

NVTE_JAX_UNITTEST_LEVEL="L2" python3 -m pytest -c $TE_PATH/tests/jax/pytest.ini -v --junitxml=$XML_LOG_DIR/pytest_jax_not_distributed.xml $TE_PATH/tests/jax -k 'not distributed' || test_fail "tests/jax/*not_distributed_*"
NVTE_JAX_UNITTEST_LEVEL="L2" python3 -m pytest -c $TE_PATH/tests/jax/pytest.ini -v --junitxml=$XML_LOG_DIR/pytest_jax_not_distributed.xml $TE_PATH/tests/jax --ignore=$TE_PATH/tests/jax/test_multi_process_ep.py -k 'not distributed' || test_fail "tests/jax/*not_distributed_*"

pip3 install -r $TE_PATH/examples/jax/mnist/requirements.txt || error_exit "Failed to install mnist requirements"
# Note: mnist intentionally does NOT set --xla_gpu_deterministic_ops because it
Expand Down
2 changes: 1 addition & 1 deletion transformer_engine/jax/cpp_extensions/router.py
Original file line number Diff line number Diff line change
Expand Up @@ -412,7 +412,7 @@ def partition(
arg_infos,
result_infos,
):
del result_infos, routing_map_format
del result_infos
grad_spec = get_padded_spec(arg_infos[2])
out_sharding = NamedSharding(mesh, PartitionSpec(*grad_spec))
arg_shardings = (arg_infos[0].sharding, arg_infos[1].sharding, arg_infos[2].sharding)
Expand Down
Loading