Lines Matching full:distributed
24 import torch.distributed as dist
83 DISTRIBUTED_TEST_PREFIX = "distributed"
120 FSDP_TEST = [test for test in TESTS if test.startswith("distributed/fsdp")]
123 "distributed/nn/jit/test_instantiator",
124 "distributed/rpc/test_faulty_agent",
125 "distributed/rpc/test_tensorpipe_agent",
126 "distributed/rpc/test_share_memory",
127 "distributed/rpc/cuda/test_tensorpipe_agent",
128 "distributed/pipeline/sync/skip/test_api",
129 "distributed/pipeline/sync/skip/test_gpipe",
130 "distributed/pipeline/sync/skip/test_inspect_skip_layout",
131 "distributed/pipeline/sync/skip/test_leak",
132 "distributed/pipeline/sync/skip/test_portal",
133 "distributed/pipeline/sync/skip/test_stash_pop",
134 "distributed/pipeline/sync/skip/test_tracker",
135 "distributed/pipeline/sync/skip/test_verify_skippables",
136 "distributed/pipeline/sync/test_balance",
137 "distributed/pipeline/sync/test_bugs",
138 "distributed/pipeline/sync/test_checkpoint",
139 "distributed/pipeline/sync/test_copy",
140 "distributed/pipeline/sync/test_deferred_batch_norm",
141 "distributed/pipeline/sync/test_dependency",
142 "distributed/pipeline/sync/test_inplace",
143 "distributed/pipeline/sync/test_microbatch",
144 "distributed/pipeline/sync/test_phony",
145 "distributed/pipeline/sync/test_pipe",
146 "distributed/pipeline/sync/test_pipeline",
147 "distributed/pipeline/sync/test_stream",
148 "distributed/pipeline/sync/test_transparency",
149 "distributed/pipeline/sync/test_worker",
150 "distributed/elastic/agent/server/test/api_test",
151 "distributed/elastic/multiprocessing/api_test",
152 "distributed/_shard/checkpoint/test_checkpoint"
153 "distributed/_shard/checkpoint/test_file_system_checkpoint"
154 "distributed/_shard/sharding_spec/test_sharding_spec",
155 "distributed/_shard/sharding_plan/test_sharding_plan",
156 "distributed/_shard/sharded_tensor/test_sharded_tensor",
157 "distributed/_shard/sharded_tensor/test_sharded_tensor_reshard",
158 "distributed/_shard/sharded_tensor/ops/test_embedding",
159 "distributed/_shard/sharded_tensor/ops/test_embedding_bag",
160 "distributed/_shard/sharded_tensor/ops/test_binary_cmp",
161 "distributed/_shard/sharded_tensor/ops/test_init",
162 "distributed/_shard/sharded_optim/test_sharded_optim",
166 "distributed/rpc/test_faulty_agent",
167 "distributed/rpc/test_tensorpipe_agent",
168 "distributed/rpc/test_share_memory",
169 "distributed/rpc/cuda/test_tensorpipe_agent",
170 "distributed/_shard/checkpoint/test_checkpoint"
171 "distributed/_shard/checkpoint/test_file_system_checkpoint"
172 "distributed/_shard/sharding_spec/test_sharding_spec",
173 "distributed/_shard/sharding_plan/test_sharding_plan",
174 "distributed/_shard/sharded_tensor/test_sharded_tensor",
175 "distributed/_shard/sharded_tensor/test_sharded_tensor_reshard",
176 "distributed/_shard/sharded_tensor/ops/test_embedding",
177 "distributed/_shard/sharded_tensor/ops/test_embedding_bag",
178 "distributed/_shard/sharded_tensor/ops/test_binary_cmp",
179 "distributed/_shard/sharded_tensor/ops/test_init",
180 "distributed/_shard/sharded_optim/test_sharded_optim",
185 "distributed/_tensor/test_attention",
819 f"Running distributed tests for the {backend} backend {with_init}"
1036 # Distributed tests are too slow, so running them x50 will cause the jobs to timeout after
1098 "distributed/test_distributed_spawn": test_distributed,
1099 "distributed/algorithms/quantization/test_quantization": test_distributed,
1100 "distributed/test_c10d_nccl": run_test_with_subprocess,
1101 "distributed/test_c10d_gloo": run_test_with_subprocess,
1102 "distributed/test_c10d_ucc": run_test_with_subprocess,
1103 "distributed/test_c10d_common": run_test_with_subprocess,
1104 "distributed/test_c10d_spawn_gloo": run_test_with_subprocess,
1105 "distributed/test_c10d_spawn_nccl": run_test_with_subprocess,
1106 "distributed/test_c10d_spawn_ucc": run_test_with_subprocess,
1107 "distributed/test_store": run_test_with_subprocess,
1108 "distributed/test_pg_wrapper": run_test_with_subprocess,
1109 "distributed/rpc/test_faulty_agent": run_test_with_subprocess,
1110 "distributed/rpc/test_tensorpipe_agent": run_test_with_subprocess,
1111 "distributed/rpc/test_share_memory": run_test_with_subprocess,
1112 "distributed/rpc/cuda/test_tensorpipe_agent": run_test_with_subprocess,
1153 "--distributed-tests",
1154 "--distributed-tests",
1156 help="Run all distributed tests",
1271 or (TEST_CONFIG == "distributed" and TEST_CUDA)
1304 "--exclude-distributed-tests",
1306 help="exclude distributed tests",
1391 # filter if there's JIT only and distributed only test options
1484 # skip all distributed tests if distributed package is not available.
1489 "PyTorch is built without distributed support.",