| .. |
|
_composable
|
[Dynamo] Replace unimplemented with unimplemented_v2 in torch/_dynamo/variables/tensor.py (#153146)
|
2025-06-09 06:27:50 +00:00 |
|
_shard
|
add support for 0 size shardedTensor and recalculate metadata from all_gather (#152583)
|
2025-05-03 17:26:29 +00:00 |
|
_tools
|
[CI] Migrate focal (ubuntu 20.04) images to jammy (ubuntu 22.04) (#154437)
|
2025-06-05 15:24:07 +00:00 |
|
algorithms
|
|
|
|
bin
|
|
|
|
checkpoint
|
Updates to HFStorageReader to use TensorStorageMetadata instead of BytesStorageMetadata (#154518)
|
2025-06-11 23:35:05 +00:00 |
|
elastic
|
Add __main__ guards to distributed tests (#154628)
|
2025-06-04 14:39:57 +00:00 |
|
flight_recorder
|
[c10d][fr] Fix another bug when we should continue when the op list is empty (#151798)
|
2025-04-22 04:43:31 +00:00 |
|
fsdp
|
[BE][DTensor] move torch.distributed._tensor import to torch.distributed.tensor in test files (#153225)
|
2025-05-09 20:40:54 +00:00 |
|
launcher
|
Add __main__ guards to distributed tests (#154628)
|
2025-06-04 14:39:57 +00:00 |
|
nn/jit
|
|
|
|
optim
|
|
|
|
pipelining
|
[PP] Fix disabled flaky tests (#154856)
|
2025-06-03 15:55:29 +00:00 |
|
rpc
|
|
|
|
tensor
|
[DTensor] Support in gradient placement for local_map() (#155181)
|
2025-06-12 17:07:04 +00:00 |
|
_test_template.py
|
[Distributed][CI] Rework continuous TestCase (#153653)
|
2025-05-25 03:49:29 +00:00 |
|
argparse_util_test.py
|
|
|
|
test_backends.py
|
|
|
|
test_c10d_common.py
|
[c10d] Allow split_group to work with non nccl backends (#152175)
|
2025-05-16 00:15:29 +00:00 |
|
test_c10d_functional_native.py
|
Add a test for AsyncCollectiveTensor handling for maybe-view ops (#152688)
|
2025-05-05 17:21:00 +00:00 |
|
test_c10d_gloo.py
|
[c10d][gloo] Enable using c10::Half for gloo (#153862)
|
2025-06-04 17:53:08 +00:00 |
|
test_c10d_logger.py
|
|
|
|
test_c10d_nccl.py
|
[c10d][fr] Add the log of thread name and thread id into fr (#155142)
|
2025-06-05 03:33:01 +00:00 |
|
test_c10d_object_collectives.py
|
|
|
|
test_c10d_ops_nccl.py
|
[Distributed][CI] Rework continuous TestCase (#153653)
|
2025-05-25 03:49:29 +00:00 |
|
test_c10d_pypg.py
|
|
|
|
test_c10d_spawn_gloo.py
|
|
|
|
test_c10d_spawn_nccl.py
|
|
|
|
test_c10d_spawn_ucc.py
|
|
|
|
test_c10d_spawn.py
|
Add __main__ guards to distributed tests (#154628)
|
2025-06-04 14:39:57 +00:00 |
|
test_c10d_ucc.py
|
[CI][CUDA][UCC] Update test_c10d_ucc.py - remove xfailIfLinux because it now succeeds (#150979)
|
2025-06-02 03:24:35 +00:00 |
|
test_collective_utils.py
|
Add __main__ guards to distributed tests (#154628)
|
2025-06-04 14:39:57 +00:00 |
|
test_composability.py
|
[Distributed][CI] Rework continuous TestCase (#153653)
|
2025-05-25 03:49:29 +00:00 |
|
test_compute_comm_reordering.py
|
[inductor][comms] skip reorder_for_locality for wait nodes (#150074)
|
2025-04-16 10:18:33 +00:00 |
|
test_control_collectives.py
|
|
|
|
test_data_parallel.py
|
|
|
|
test_device_mesh.py
|
[device_mesh] improve device selection logic (#150897)
|
2025-05-14 06:29:16 +00:00 |
|
test_distributed_spawn.py
|
|
|
|
test_dynamo_distributed.py
|
[dynamo] unimplemented -> unimplemented_v2 in variables/builtin.py (#151145)
|
2025-04-16 17:16:05 +00:00 |
|
test_fake_pg.py
|
[BE][DTensor] move torch.distributed._tensor import to torch.distributed.tensor in test files (#153225)
|
2025-05-09 20:40:54 +00:00 |
|
test_functional_api.py
|
[inductor][dynamo] Include operator name in size/stride/alignment assertion (#152353)
|
2025-06-03 19:21:15 +00:00 |
|
test_inductor_collectives.py
|
[Graph Partition] Maintain relative order within partition during reordering (#153111)
|
2025-05-09 18:49:53 +00:00 |
|
test_launcher.py
|
|
|
|
test_multi_threaded_pg.py
|
|
|
|
test_nccl.py
|
|
|
|
test_nvshmem.py
|
[SymmMem] Enable NVSHMEM for Triton (#155506)
|
2025-06-12 00:22:49 +00:00 |
|
test_pg_wrapper.py
|
|
|
|
test_serialization.py
|
|
|
|
test_store.py
|
c10d/Store: add nonblocking mode to queue_pop (#151485)
|
2025-04-18 02:14:50 +00:00 |
|
test_symmetric_memory.py
|
[CI][CUDA] Migrate remaining cu118 jobs to cu128 (#154169)
|
2025-06-02 20:22:14 +00:00 |
50d8168c8b