deepseekmirror/DeepSeek-V3
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-V3.git synced 2025-04-20 02:28:57 -04:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

sort filename to reduce memory costs

Browse Source
This commit is contained in:
Yang Wang 2024-12-26 23:14:44 +08:00 committed by GitHub
parent 1e3a83629e
commit e6e66fd23f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
inference/fp8_cast_bf16.py
View File

@ -30,6 +30,7 @@ def main(fp8_path, bf16_path):
return loaded_files[file_name][tensor_name] return loaded_files[file_name][tensor_name]
safetensor_files = list(glob(os.path.join(fp8_path, "*.safetensors"))) safetensor_files = list(glob(os.path.join(fp8_path, "*.safetensors")))
safetensor_files.sort()
for safetensor_file in tqdm(safetensor_files): for safetensor_file in tqdm(safetensor_files):
file_name = os.path.basename(safetensor_file) file_name = os.path.basename(safetensor_file)
current_state_dict = load_file(safetensor_file, device="cuda") current_state_dict = load_file(safetensor_file, device="cuda")