KV 融合实现完成。改动总结： 速度微弱提升psnr略微上升
attention.py — 3处改动： 1. __init__ 添加 _kv_fused = False 标志 2.新增 fuse_kv() 方法：将 to_k + to_v → to_kv，同时处理 _ip/_as/_aa 辅助 KV 对 2. bmm_forward 两个分支加_kv_fused 判断，用to_kv().chunk(2, dim=-1) 替代分别调用
This commit is contained in:
@@ -1,10 +1,10 @@
|
||||
2026-02-10 22:35:08.834827: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
||||
2026-02-10 22:35:08.884699: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
||||
2026-02-10 22:35:08.884743: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
||||
2026-02-10 22:35:08.886076: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
||||
2026-02-10 22:35:08.893623: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
||||
2026-02-11 11:59:27.241485: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
||||
2026-02-11 11:59:27.291755: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
||||
2026-02-11 11:59:27.291807: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
||||
2026-02-11 11:59:27.293169: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
||||
2026-02-11 11:59:27.300838: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
||||
2026-02-10 22:35:09.824417: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
||||
2026-02-11 11:59:28.228009: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
||||
Global seed set to 123
|
||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
||||
>>> Prepared model loaded.
|
||||
@@ -25,9 +25,96 @@ INFO:root:***** Configing Data *****
|
||||
>>> unitree_g1_pack_camera: data stats loaded.
|
||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
||||
>>> Dataset is successfully loaded ...
|
||||
✓ KV fused: 66 attention layers
|
||||
>>> Generate 16 frames under each generation ...
|
||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
||||
|
||||
|
||||
0%| | 0/11 [00:00<?, ?it/s]
|
||||
9%|▉ | 1/11 [00:34<05:40, 34.05s/it]>>> Step 0: generating actions ...
|
||||
>>> Step 0: interacting with world model ...
|
||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||
>>> Step 1: generating actions ...
|
||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
||||
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
||||
DEBUG:PIL.Image:Importing SunImagePlugin
|
||||
DEBUG:PIL.Image:Importing TgaImagePlugin
|
||||
DEBUG:PIL.Image:Importing TiffImagePlugin
|
||||
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||
|
||||
18%|█▊ | 2/11 [01:08<05:07, 34.17s/it]
|
||||
27%|██▋ | 3/11 [01:42<04:33, 34.16s/it]
|
||||
36%|███▋ | 4/11 [02:16<03:59, 34.18s/it]
|
||||
45%|████▌ | 5/11 [02:50<03:24, 34.14s/it]
|
||||
55%|█████▍ | 6/11 [03:24<02:50, 34.10s/it]
|
||||
64%|██████▎ | 7/11 [03:58<02:16, 34.07s/it]
|
||||
73%|███████▎ | 8/11 [04:32<01:42, 34.03s/it]
|
||||
82%|████████▏ | 9/11 [05:06<01:08, 34.02s/it]
|
||||
91%|█████████ | 10/11 [05:40<00:34, 34.04s/it]
|
||||
100%|██████████| 11/11 [06:14<00:00, 34.03s/it]
|
||||
100%|██████████| 11/11 [06:14<00:00, 34.07s/it]
|
||||
>>> Step 1: interacting with world model ...
|
||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||
>>> Step 2: generating actions ...
|
||||
>>> Step 2: interacting with world model ...
|
||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||
>>> Step 3: generating actions ...
|
||||
>>> Step 3: interacting with world model ...
|
||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||
>>> Step 4: generating actions ...
|
||||
>>> Step 4: interacting with world model ...
|
||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||
>>> Step 5: generating actions ...
|
||||
>>> Step 5: interacting with world model ...
|
||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||
>>> Step 6: generating actions ...
|
||||
>>> Step 6: interacting with world model ...
|
||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||
>>> Step 7: generating actions ...
|
||||
>>> Step 7: interacting with world model ...
|
||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||
|
||||
Reference in New Issue
Block a user