github
/
minimind
mirror of https://github.com/jingyaogong/minimind.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[fix] lora compile

pull/738/head
jingyaogong 2026-04-10 00:01:21 +08:00
parent b2488e6440
commit e796b8028a
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
trainer/train_lora.py
View File

@ -97,7 +97,6 @@ if __name__ == "__main__":
parser.add_argument('--from_resume', default=0, type=int, choices=[0, 1], help="是否自动检测&续训（0=否，1=是）") parser.add_argument('--from_resume', default=0, type=int, choices=[0, 1], help="是否自动检测&续训（0=否，1=是）")
parser.add_argument("--use_wandb", action="store_true", help="是否使用wandb") parser.add_argument("--use_wandb", action="store_true", help="是否使用wandb")
parser.add_argument("--wandb_project", type=str, default="MiniMind-LoRA", help="wandb项目名") parser.add_argument("--wandb_project", type=str, default="MiniMind-LoRA", help="wandb项目名")
# PS：多卡 DDP + LoRA 场景下建议关闭 use_compile，避免触发 torch.compile 的兼容性问题
parser.add_argument("--use_compile", default=0, type=int, choices=[0, 1], help="是否使用torch.compile加速（0=否，1=是）") parser.add_argument("--use_compile", default=0, type=int, choices=[0, 1], help="是否使用torch.compile加速（0=否，1=是）")
args = parser.parse_args() args = parser.parse_args()
@ -162,8 +161,8 @@ if __name__ == "__main__":
# ========== 8. 编译和分布式包装 ========== # ========== 8. 编译和分布式包装 ==========
if args.use_compile == 1: if args.use_compile == 1:
model = torch.compile(model) args.use_compile = 0
Logger('torch.compile enabled') Logger('[LoRA] monkey-patch forward 与 torch.compile 不兼容，use_compile 已自动关闭')
if dist.is_initialized(): if dist.is_initialized():
model._ddp_params_and_buffers_to_ignore = {"freqs_cos", "freqs_sin"} model._ddp_params_and_buffers_to_ignore = {"freqs_cos", "freqs_sin"}
model = DistributedDataParallel(model, device_ids=[local_rank]) model = DistributedDataParallel(model, device_ids=[local_rank])