[npu] add npu fsdp example (#6697)

Author: addsubmuldiv

examples/ascend/train/qwen3_lora_fsdp/fsdp.json

@@ -0,0 +1,26 @@
+{
+  "compute_environment": "LOCAL_MACHINE",
+  "debug": false,
+  "distributed_type": "FSDP",
+  "downcast_bf16": "no",
+  "mixed_precision": "bf16",
+  "num_machines": 1,
+  "num_processes": 8,
+  "machine_rank": 0,
+  "rdzv_backend": "static",
+  "same_network": true,
+  "use_cpu": false,
+  "fsdp_config": {
+    "fsdp_auto_wrap_policy": "TRANSFORMER_BASED_WRAP",
+    "fsdp_transformer_cls_names_to_wrap": "Qwen3DecoderLayer",
+    "fsdp_sharding_strategy": "FULL_SHARD",
+    "fsdp_backward_prefetch": "BACKWARD_PRE",
+    "fsdp_forward_prefetch": true,
+    "fsdp_limit_all_gathers": true,
+    "fsdp_state_dict_type": "FULL_STATE_DICT",
+    "fsdp_sync_module_states": true,
+    "fsdp_cpu_ram_efficient_loading": true,
+    "fsdp_use_orig_params": true,
+    "fsdp_offload_params": false
+  }
+}

examples/ascend/train/qwen3_lora_fsdp/train.sh

@@ -0,0 +1,26 @@
+# hardware: Atlas 900 A2
+export TASK_QUEUE_ENABLE=2
+export CPU_AFFINITY_CONF=2
+ASCEND_RT_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
+accelerate launch --config_file "./examples/ascend/train/qwen3_lora_fsdp/fsdp.json" \
+    swift/cli/sft.py \
+    --model 'Qwen/Qwen3-32B' \
+    --train_type lora \
+    --dataset 'swift/self-cognition#1000' \
+    --torch_dtype bfloat16 \
+    --per_device_train_batch_size 10 \
+    --gradient_accumulation_steps 2 \
+    --gradient_checkpointing true \
+    --gradient_checkpointing_kwargs '{"use_reentrant": false}' \
+    --max_length 1200 \
+    --num_train_epochs 2 \
+    --eval_strategy no \
+    --save_steps 500 \
+    --logging_steps 1 \
+    --dataloader_num_workers 8 \
+    --dataset_num_proc 8 \
+    --save_total_limit 2 \
+    --save_only_model true \
+    --output_dir output \
+    --attn_impl 'flash_attention_2' \
+    --packing true