chore: import upstream snapshot with attribution

swift/config/fsdp2.json

@@ -0,0 +1,25 @@
+{
+    "_description": "FSDP2 configuration for distributed training (PyTorch native FSDP v2)",
+    "_requires": "torch>=2.4.0",
+    "_note": "This is the recommended configuration for multi-GPU training without CPU offloading. NOTE: When using FSDP2, do NOT use --gradient_checkpointing, use activation_checkpointing in fsdp_config instead.",
+
+    "_param_docs": {
+        "fsdp": "FSDP strategy string. Options: 'full_shard' (ZeRO-3 style, shards params+grads+optimizer), 'shard_grad_op' (ZeRO-2 style, shards grads+optimizer only). Add 'auto_wrap' to enable automatic layer wrapping. Add 'offload' to enable CPU offloading.",
+        "fsdp_version": "FSDP version. Use 2 for PyTorch native FSDP2 (recommended). FSDP2 uses DTensor for per-parameter sharding, supports LoRA/QLoRA natively.",
+        "auto_wrap_policy": "How to wrap model layers. 'TRANSFORMER_BASED_WRAP' wraps transformer decoder layers (from model._no_split_modules). 'SIZE_BASED_WRAP' wraps modules exceeding min_num_params.",
+        "cpu_ram_efficient_loading": "If true, only rank 0 loads full model weights, then broadcasts to other ranks. Reduces CPU RAM usage during initialization.",
+        "state_dict_type": "'SHARDED_STATE_DICT' (recommended): each rank saves its own shard without extra communication. 'FULL_STATE_DICT': gathers full model on rank 0 (higher memory, slower).",
+        "reshard_after_forward": "true = FULL_SHARD (ZeRO-3), reshards params after forward pass. false = SHARD_GRAD_OP (ZeRO-2), keeps params gathered during forward/backward.",
+        "activation_checkpointing": "Use FSDP's native activation checkpointing instead of gradient_checkpointing. This is the correct way to save memory with FSDP."
+    },
+
+    "fsdp": "full_shard auto_wrap",
+    "fsdp_config": {
+        "fsdp_version": 2,
+        "reshard_after_forward": true,
+        "auto_wrap_policy": "TRANSFORMER_BASED_WRAP",
+        "cpu_ram_efficient_loading": true,
+        "state_dict_type": "SHARDED_STATE_DICT",
+        "activation_checkpointing": true
+    }
+}

swift/config/zero0.json

@@ -0,0 +1,31 @@
+{
+    "fp16": {
+        "enabled": "auto",
+        "loss_scale": 0,
+        "loss_scale_window": 1000,
+        "initial_scale_power": 16,
+        "hysteresis": 2,
+        "min_loss_scale": 1
+    },
+
+    "bf16": {
+        "enabled": "auto"
+    },
+
+    "zero_optimization": {
+        "stage": 0,
+        "allgather_partitions": true,
+        "allgather_bucket_size": 2e8,
+        "overlap_comm": false,
+        "reduce_scatter": true,
+        "reduce_bucket_size": 2e8,
+        "contiguous_gradients": true
+    },
+
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+}

swift/config/zero1.json

@@ -0,0 +1,35 @@
+{
+    "fp16": {
+        "enabled": "auto",
+        "loss_scale": 0,
+        "loss_scale_window": 1000,
+        "initial_scale_power": 16,
+        "hysteresis": 2,
+        "min_loss_scale": 1
+    },
+
+    "bf16": {
+        "enabled": "auto"
+    },
+
+    "zero_optimization": {
+        "stage": 1,
+        "offload_optimizer": {
+            "device": "none",
+            "pin_memory": true
+        },
+        "allgather_partitions": true,
+        "allgather_bucket_size": 2e8,
+        "overlap_comm": false,
+        "reduce_scatter": true,
+        "reduce_bucket_size": 2e8,
+        "contiguous_gradients": true
+    },
+
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+}

swift/config/zero2.json

@@ -0,0 +1,35 @@
+{
+    "fp16": {
+        "enabled": "auto",
+        "loss_scale": 0,
+        "loss_scale_window": 1000,
+        "initial_scale_power": 16,
+        "hysteresis": 2,
+        "min_loss_scale": 1
+    },
+
+    "bf16": {
+        "enabled": "auto"
+    },
+
+    "zero_optimization": {
+        "stage": 2,
+        "offload_optimizer": {
+            "device": "none",
+            "pin_memory": true
+        },
+        "allgather_partitions": true,
+        "allgather_bucket_size": 2e8,
+        "overlap_comm": false,
+        "reduce_scatter": true,
+        "reduce_bucket_size": 2e8,
+        "contiguous_gradients": true
+    },
+
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+}

swift/config/zero2_offload.json

@@ -0,0 +1,35 @@
+{
+    "fp16": {
+        "enabled": "auto",
+        "loss_scale": 0,
+        "loss_scale_window": 1000,
+        "initial_scale_power": 16,
+        "hysteresis": 2,
+        "min_loss_scale": 1
+    },
+
+    "bf16": {
+        "enabled": "auto"
+    },
+
+    "zero_optimization": {
+        "stage": 2,
+        "offload_optimizer": {
+            "device": "cpu",
+            "pin_memory": true
+        },
+        "allgather_partitions": true,
+        "allgather_bucket_size": 2e8,
+        "overlap_comm": false,
+        "reduce_scatter": true,
+        "reduce_bucket_size": 2e8,
+        "contiguous_gradients": true
+    },
+
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+}

swift/config/zero3.json

@@ -0,0 +1,44 @@
+{
+    "fp16": {
+        "enabled": "auto",
+        "loss_scale": 0,
+        "loss_scale_window": 1000,
+        "initial_scale_power": 16,
+        "hysteresis": 2,
+        "min_loss_scale": 1
+    },
+
+    "bf16": {
+        "enabled": "auto"
+    },
+
+    "zero_optimization": {
+        "stage": 3,
+        "offload_optimizer": {
+            "device": "none",
+            "pin_memory": true
+        },
+        "offload_param": {
+            "device": "none",
+            "pin_memory": true
+        },
+        "overlap_comm": false,
+        "contiguous_gradients": true,
+        "sub_group_size": 1e9,
+        "reduce_bucket_size": "auto",
+        "zero_quantized_weights": false,
+        "zero_quantized_gradients": false,
+        "stage3_prefetch_bucket_size": "auto",
+        "stage3_param_persistence_threshold": "auto",
+        "stage3_max_live_parameters": 1e9,
+        "stage3_max_reuse_distance": 1e9,
+        "stage3_gather_16bit_weights_on_model_save": true
+    },
+
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+}

swift/config/zero3_offload.json

@@ -0,0 +1,42 @@
+{
+    "fp16": {
+        "enabled": "auto",
+        "loss_scale": 0,
+        "loss_scale_window": 1000,
+        "initial_scale_power": 16,
+        "hysteresis": 2,
+        "min_loss_scale": 1
+    },
+
+    "bf16": {
+        "enabled": "auto"
+    },
+
+    "zero_optimization": {
+        "stage": 3,
+        "offload_optimizer": {
+            "device": "cpu",
+            "pin_memory": true
+        },
+        "offload_param": {
+            "device": "cpu",
+            "pin_memory": true
+        },
+        "overlap_comm": false,
+        "contiguous_gradients": true,
+        "sub_group_size": 1e9,
+        "reduce_bucket_size": "auto",
+        "stage3_prefetch_bucket_size": "auto",
+        "stage3_param_persistence_threshold": "auto",
+        "stage3_max_live_parameters": 1e9,
+        "stage3_max_reuse_distance": 1e9,
+        "stage3_gather_16bit_weights_on_model_save": true
+    },
+
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+}