CHANGELOG.md
CITATION.cff
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
MANIFEST.in
README.md
SECURITY.md
THIRD_PARTY_NOTICES.md
pyproject.toml
docs/api.md
docs/compatibility.md
docs/fault_injection.md
docs/gemini.md
docs/index.md
docs/moe_execution_regimes.md
docs/release.md
docs/scout.md
docs/torchrun_resiliency.md
docs/validation.md
examples/README.md
examples/__init__.py
examples/production_loops/__init__.py
examples/production_loops/_common.py
examples/production_loops/deepspeed.py
examples/production_loops/megatron.py
examples/production_loops/pytorch.py
examples/production_loops/torchtitan.py
examples/torchrun/README.md
examples/torchrun/__init__.py
examples/torchrun/adapter_bootstrap/__init__.py
examples/torchrun/adapter_bootstrap/_validation.py
examples/torchrun/adapter_bootstrap/framework_worker.py
examples/torchrun/adapter_bootstrap/matrix.py
examples/torchrun/adapter_bootstrap/smoke.py
examples/torchrun/resiliency_cycle/__init__.py
examples/torchrun/resiliency_cycle/pressure.py
examples/torchrun/resiliency_cycle/campaigns/framework_restart_replacement.json
examples/torchrun/resiliency_cycle/campaigns/single_node_pressure.json
examples/torchrun/resiliency_cycle/harness/__init__.py
examples/torchrun/resiliency_cycle/harness/artifacts.py
examples/torchrun/resiliency_cycle/harness/campaign.py
examples/torchrun/resiliency_cycle/harness/faults.py
examples/torchrun/resiliency_cycle/harness/launch.py
examples/torchrun/resiliency_cycle/harness/replay_fault.py
examples/torchrun/resiliency_cycle/harness/runtime.py
examples/torchrun/resiliency_cycle/harness/verify.py
examples/torchrun/resiliency_cycle/harness/worker.py
examples/torchrun/resiliency_cycle/harness/frameworks/__init__.py
examples/torchrun/resiliency_cycle/harness/frameworks/deepspeed.py
examples/torchrun/resiliency_cycle/harness/frameworks/megatron.py
examples/torchrun/resiliency_cycle/harness/frameworks/pytorch.py
examples/torchrun/resiliency_cycle/harness/frameworks/torchtitan.py
lm_resiliency/__init__.py
lm_resiliency/_feature_wiring.py
lm_resiliency/adapters.py
lm_resiliency/api.py
lm_resiliency/cadence.py
lm_resiliency/dispatch.py
lm_resiliency/experimental.py
lm_resiliency/handle.py
lm_resiliency/lifecycle.py
lm_resiliency/manager_api.py
lm_resiliency/orchestration.py
lm_resiliency/py.typed
lm_resiliency/quickstart.py
lm_resiliency/recovery.py
lm_resiliency.egg-info/PKG-INFO
lm_resiliency.egg-info/SOURCES.txt
lm_resiliency.egg-info/dependency_links.txt
lm_resiliency.egg-info/entry_points.txt
lm_resiliency.egg-info/requires.txt
lm_resiliency.egg-info/top_level.txt
lm_resiliency/checkpointing/__init__.py
lm_resiliency/checkpointing/_disk_format.py
lm_resiliency/checkpointing/buffer.py
lm_resiliency/checkpointing/config.py
lm_resiliency/checkpointing/copy.py
lm_resiliency/checkpointing/disk.py
lm_resiliency/checkpointing/durable.py
lm_resiliency/checkpointing/manager.py
lm_resiliency/checkpointing/replication.py
lm_resiliency/checkpointing/rng.py
lm_resiliency/checkpointing/state_dict.py
lm_resiliency/checkpointing/transfer.py
lm_resiliency/cli/__init__.py
lm_resiliency/cli/discover_moe_regimes.py
lm_resiliency/detection/__init__.py
lm_resiliency/detection/_utils.py
lm_resiliency/detection/all_to_all_replay.py
lm_resiliency/detection/c3.py
lm_resiliency/detection/collective_timing.py
lm_resiliency/detection/communication_localizer.py
lm_resiliency/detection/config.py
lm_resiliency/detection/config_drift.py
lm_resiliency/detection/cross_pg.py
lm_resiliency/detection/hang_detector.py
lm_resiliency/detection/hang_instrumentation.py
lm_resiliency/detection/ib_topology.py
lm_resiliency/detection/layer_replay.py
lm_resiliency/detection/moe_regimes.py
lm_resiliency/detection/oob_service.py
lm_resiliency/detection/op_tracker.py
lm_resiliency/detection/optimizer_step.py
lm_resiliency/detection/peer_group.py
lm_resiliency/detection/replay_analysis.py
lm_resiliency/detection/replay_harness.py
lm_resiliency/detection/replay_shapes.py
lm_resiliency/detection/reports.py
lm_resiliency/detection/sdc_localizer.py
lm_resiliency/detection/stage_instrumentation.py
lm_resiliency/detection/straggler_localizer.py
lm_resiliency/detection/switch_localizer.py
lm_resiliency/detection/temporal.py
lm_resiliency/detection/topology.py
lm_resiliency/detection/health/__init__.py
lm_resiliency/detection/health/config.py
lm_resiliency/detection/health/monitor.py
lm_resiliency/detection/health/sources.py
lm_resiliency/fault_injection/__init__.py
lm_resiliency/fault_injection/_json.py
lm_resiliency/fault_injection/config.py
lm_resiliency/fault_injection/executors.py
lm_resiliency/fault_injection/frameworks.py
lm_resiliency/fault_injection/injector.py
lm_resiliency/fault_injection/local.py
lm_resiliency/fault_injection/reports.py
lm_resiliency/fault_injection/state.py
lm_resiliency/integrations/__init__.py
lm_resiliency/integrations/_checkpoint_certification.py
lm_resiliency/integrations/_common.py
lm_resiliency/integrations/deepspeed/__init__.py
lm_resiliency/integrations/deepspeed/adapter.py
lm_resiliency/integrations/deepspeed/training.py
lm_resiliency/integrations/megatron/__init__.py
lm_resiliency/integrations/megatron/adapter.py
lm_resiliency/integrations/megatron/training.py
lm_resiliency/integrations/pytorch/__init__.py
lm_resiliency/integrations/pytorch/fsdp.py
lm_resiliency/integrations/pytorch/gradient_replay.py
lm_resiliency/integrations/torchrun/__init__.py
lm_resiliency/integrations/torchrun/_protocol.py
lm_resiliency/integrations/torchrun/_simple_runtime.py
lm_resiliency/integrations/torchrun/coordinator.py
lm_resiliency/integrations/torchrun/launch.py
lm_resiliency/integrations/torchrun/worker_adapter.py
lm_resiliency/integrations/torchrun/_worker_bootstrap/__init__.py
lm_resiliency/integrations/torchrun/_worker_bootstrap/sitecustomize.py
lm_resiliency/integrations/torchtitan/__init__.py
lm_resiliency/integrations/torchtitan/adapter.py
lm_resiliency/integrations/torchtitan/gradient_replay.py
lm_resiliency/integrations/torchtitan/training.py