Merge 655d4705eb into a3c7b01cc0

`device_type` currently only distinguishes "cuda" from "cpu", so running
with `--device mps` on Apple Silicon falls into the "cpu" branch, disables
autocast entirely and forces fp32 training.

Changes (9 files, mechanical):
- `device_type` now resolves to cuda / mps / cpu
- `torch.cuda.amp.autocast(...)` -> `torch.amp.autocast(device_type, ...)`
- `torch.cuda.amp.GradScaler(...)` -> `torch.amp.GradScaler(device_type, ...)`,
  enabled only for CUDA + fp16 (MPS has no gradient scaler)
- `web_demo.py` device selection now prefers mps when available

This also silences the `torch.cuda.amp.*` deprecation warnings on torch 2.x.
CUDA behaviour is unchanged.

Measured on Apple M5 Pro (24GB), hidden_size=512 / 8 layers, bs=16, seq=512:
- before (fp32, no autocast): 11,784 tok/s
- after  (bf16 autocast):     15,492 tok/s   (+31%)

Verified end-to-end on MPS: pretrain, full_sft, lora, dpo, ppo, grpo,
distillation and agent RL all run to completion, and the resulting weights
export correctly to transformers / GGUF.

Note for macOS users: `--num_workers 0` is currently required, as DataLoader
worker processes deadlock on macOS + Python 3.12 due to fork safety.

scripts/web_demo.py

@@ -67,7 +67,7 @@ st.markdown("""
     </style>
 """, unsafe_allow_html=True)
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
+device = "cuda" if torch.cuda.is_available() else ("mps" if torch.backends.mps.is_available() else "cpu")
 
 # 多语言文本
 LANG_TEXTS = {

trainer/train_agent.py

@@ -427,9 +427,9 @@ if __name__ == "__main__":
                                max_seq_len=args.max_seq_len + args.max_gen_len, use_moe=bool(args.use_moe))
     ckp_data = lm_checkpoint(lm_config, weight=args.save_weight, save_dir='../checkpoints') if args.from_resume == 1 else None
 
-    device_type = "cuda" if "cuda" in args.device else "cpu"
+    device_type = "cuda" if "cuda" in args.device else ("mps" if "mps" in args.device else "cpu")
     dtype = torch.bfloat16 if args.dtype == "bfloat16" else torch.float16
-    autocast_ctx = nullcontext() if device_type == "cpu" else torch.cuda.amp.autocast(dtype=dtype)
+    autocast_ctx = nullcontext() if device_type == "cpu" else torch.amp.autocast(device_type, dtype=dtype)
 
     wandb = None
     if args.use_wandb and is_main_process():

trainer/train_distillation.py

@@ -188,9 +188,9 @@ if __name__ == "__main__":
     ckp_data = lm_checkpoint(lm_config_student, weight=args.save_weight, save_dir='../checkpoints') if args.from_resume==1 else None
     
     # ========== 3. 设置混合精度 ==========
-    device_type = "cuda" if "cuda" in args.device else "cpu"
+    device_type = "cuda" if "cuda" in args.device else ("mps" if "mps" in args.device else "cpu")
     dtype = torch.bfloat16 if args.dtype == "bfloat16" else torch.float16
-    autocast_ctx = nullcontext() if device_type == "cpu" else torch.cuda.amp.autocast(dtype=dtype)
+    autocast_ctx = nullcontext() if device_type == "cpu" else torch.amp.autocast(device_type, dtype=dtype)
     
     # ========== 4. 配wandb ==========
     wandb = None
@@ -210,7 +210,7 @@ if __name__ == "__main__":
     Logger(f'教师模型总参数量：{sum(p.numel() for p in teacher_model.parameters()) / 1e6:.3f} M')
     train_ds = SFTDataset(args.data_path, tokenizer, max_length=args.max_seq_len)
     train_sampler = DistributedSampler(train_ds) if dist.is_initialized() else None
-    scaler = torch.cuda.amp.GradScaler(enabled=(args.dtype == 'float16'))
+    scaler = torch.amp.GradScaler(device_type, enabled=(args.dtype == 'float16' and device_type == 'cuda'))
     optimizer = optim.AdamW(model.parameters(), lr=args.learning_rate)
     
     # ========== 6. 从ckp恢复状态 ==========

trainer/train_dpo.py

@@ -166,9 +166,9 @@ if __name__ == "__main__":
     ckp_data = lm_checkpoint(lm_config, weight=args.save_weight, save_dir='../checkpoints') if args.from_resume==1 else None
     
     # ========== 3. 设置混合精度 ==========
-    device_type = "cuda" if "cuda" in args.device else "cpu"
+    device_type = "cuda" if "cuda" in args.device else ("mps" if "mps" in args.device else "cpu")
     dtype = torch.bfloat16 if args.dtype == "bfloat16" else torch.float16
-    autocast_ctx = nullcontext() if device_type == "cpu" else torch.cuda.amp.autocast(dtype=dtype)
+    autocast_ctx = nullcontext() if device_type == "cpu" else torch.amp.autocast(device_type, dtype=dtype)
     
     # ========== 4. 配wandb ==========
     wandb = None
@@ -190,7 +190,7 @@ if __name__ == "__main__":
     
     train_ds = DPODataset(args.data_path, tokenizer, max_length=args.max_seq_len)
     train_sampler = DistributedSampler(train_ds) if dist.is_initialized() else None
-    scaler = torch.cuda.amp.GradScaler(enabled=(args.dtype == 'float16'))
+    scaler = torch.amp.GradScaler(device_type, enabled=(args.dtype == 'float16' and device_type == 'cuda'))
     optimizer = optim.AdamW(model.parameters(), lr=args.learning_rate)
     
     # ========== 6. 从ckp恢复状态 ==========

trainer/train_full_sft.py

@@ -119,9 +119,9 @@ if __name__ == "__main__":
     ckp_data = lm_checkpoint(lm_config, weight=args.save_weight, save_dir='../checkpoints') if args.from_resume==1 else None
     
     # ========== 3. 设置混合精度 ==========
-    device_type = "cuda" if "cuda" in args.device else "cpu"
+    device_type = "cuda" if "cuda" in args.device else ("mps" if "mps" in args.device else "cpu")
     dtype = torch.bfloat16 if args.dtype == "bfloat16" else torch.float16
-    autocast_ctx = nullcontext() if device_type == "cpu" else torch.cuda.amp.autocast(dtype=dtype)
+    autocast_ctx = nullcontext() if device_type == "cpu" else torch.amp.autocast(device_type, dtype=dtype)
     
     # ========== 4. 配wandb ==========
     wandb = None
@@ -136,7 +136,7 @@ if __name__ == "__main__":
     model, tokenizer = init_model(lm_config, args.from_weight, device=args.device)
     train_ds = SFTDataset(args.data_path, tokenizer, max_length=args.max_seq_len)
     train_sampler = DistributedSampler(train_ds) if dist.is_initialized() else None
-    scaler = torch.cuda.amp.GradScaler(enabled=(args.dtype == 'float16'))
+    scaler = torch.amp.GradScaler(device_type, enabled=(args.dtype == 'float16' and device_type == 'cuda'))
     optimizer = optim.AdamW(model.parameters(), lr=args.learning_rate)
     
     # ========== 6. 从ckp恢复状态 ==========

trainer/train_grpo.py

@@ -256,9 +256,9 @@ if __name__ == "__main__":
     ckp_data = lm_checkpoint(lm_config, weight=args.save_weight, save_dir='../checkpoints') if args.from_resume==1 else None
     
     # ========== 3. 设置混合精度 ==========
-    device_type = "cuda" if "cuda" in args.device else "cpu"
+    device_type = "cuda" if "cuda" in args.device else ("mps" if "mps" in args.device else "cpu")
     dtype = torch.bfloat16 if args.dtype == "bfloat16" else torch.float16
-    autocast_ctx = nullcontext() if device_type == "cpu" else torch.cuda.amp.autocast(dtype=dtype)
+    autocast_ctx = nullcontext() if device_type == "cpu" else torch.amp.autocast(device_type, dtype=dtype)
     
     # ========== 4. 配wandb ==========
     wandb = None

trainer/train_lora.py

@@ -112,9 +112,9 @@ if __name__ == "__main__":
     ckp_data = lm_checkpoint(lm_config, weight=args.lora_name, save_dir='../checkpoints') if args.from_resume==1 else None
     
     # ========== 3. 设置混合精度 ==========
-    device_type = "cuda" if "cuda" in args.device else "cpu"
+    device_type = "cuda" if "cuda" in args.device else ("mps" if "mps" in args.device else "cpu")
     dtype = torch.bfloat16 if args.dtype == "bfloat16" else torch.float16
-    autocast_ctx = nullcontext() if device_type == "cpu" else torch.cuda.amp.autocast(dtype=dtype)
+    autocast_ctx = nullcontext() if device_type == "cpu" else torch.amp.autocast(device_type, dtype=dtype)
     
     # ========== 4. 配wandb ==========
     wandb = None
@@ -148,7 +148,7 @@ if __name__ == "__main__":
     # ========== 6. 定义数据和优化器 ==========
     train_ds = SFTDataset(args.data_path, tokenizer, max_length=args.max_seq_len)
     train_sampler = DistributedSampler(train_ds) if dist.is_initialized() else None
-    scaler = torch.cuda.amp.GradScaler(enabled=(args.dtype == 'float16'))
+    scaler = torch.amp.GradScaler(device_type, enabled=(args.dtype == 'float16' and device_type == 'cuda'))
     optimizer = optim.AdamW(lora_params, lr=args.learning_rate)
     
     # ========== 7. 从ckp恢复状态 ==========

trainer/train_ppo.py

@@ -364,9 +364,9 @@ if __name__ == "__main__":
     ckp_data = lm_checkpoint(lm_config, weight=args.save_weight, save_dir='../checkpoints') if args.from_resume==1 else None
     
     # ========== 3. 设置混合精度 ==========
-    device_type = "cuda" if "cuda" in args.device else "cpu"
+    device_type = "cuda" if "cuda" in args.device else ("mps" if "mps" in args.device else "cpu")
     dtype = torch.bfloat16 if args.dtype == "bfloat16" else torch.float16
-    autocast_ctx = nullcontext() if device_type == "cpu" else torch.cuda.amp.autocast(dtype=dtype)
+    autocast_ctx = nullcontext() if device_type == "cpu" else torch.amp.autocast(device_type, dtype=dtype)
     
     # ========== 4. 配wandb ==========
     wandb = None

trainer/train_pretrain.py

@@ -118,9 +118,9 @@ if __name__ == "__main__":
     ckp_data = lm_checkpoint(lm_config, weight=args.save_weight, save_dir='../checkpoints') if args.from_resume==1 else None
     
     # ========== 3. 设置混合精度 ==========
-    device_type = "cuda" if "cuda" in args.device else "cpu"
+    device_type = "cuda" if "cuda" in args.device else ("mps" if "mps" in args.device else "cpu")
     dtype = torch.bfloat16 if args.dtype == "bfloat16" else torch.float16
-    autocast_ctx = nullcontext() if device_type == "cpu" else torch.cuda.amp.autocast(dtype=dtype)
+    autocast_ctx = nullcontext() if device_type == "cpu" else torch.amp.autocast(device_type, dtype=dtype)
     
     # ========== 4. 配wandb ==========
     wandb = None
@@ -135,7 +135,7 @@ if __name__ == "__main__":
     model, tokenizer = init_model(lm_config, args.from_weight, device=args.device)
     train_ds = PretrainDataset(args.data_path, tokenizer, max_length=args.max_seq_len)
     train_sampler = DistributedSampler(train_ds) if dist.is_initialized() else None
-    scaler = torch.cuda.amp.GradScaler(enabled=(args.dtype == 'float16'))
+    scaler = torch.amp.GradScaler(device_type, enabled=(args.dtype == 'float16' and device_type == 'cuda'))
     optimizer = optim.AdamW(model.parameters(), lr=args.learning_rate)
     
     # ========== 6. 从ckp恢复状态 ==========