deepseekmirror/DeepSeek-VL2
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-VL2.git synced 2025-02-23 06:09:04 -05:00
Code Issues Actions Packages Projects Releases Wiki Activity
20 Commits 1 Branch 0 Tags 32 MiB
8c69318fc7
Commit Graph

7 Commits

Author SHA1 Message Date
Abubakar Sattar
8c69318fc7
Fixed a typo in Update inference.py 
Fixed a typo in Update inference.py

Prefilling was misspelled here.

parser.add_argument("--chunk_size", type=int, default=-1,
                        help="chunk size for the model for prefiiling. "
                             "When using 40G gpu for vl2-small, set a chunk_size for incremental_prefilling."
                             "Otherwise, default value is -1, which means we do not use incremental_prefilling.")
 2025-01-29 14:53:43 +05:00
charlescxk
c74816ad22 fix typo 2025-01-29 16:02:52 +08:00
StevenLiuWen
66ec91081c Update inference.py 2024-12-30 14:48:51 +08:00
StevenLiuWen
9789f97283 remove clear_cuda_cache in forward 2024-12-30 14:19:34 +08:00
StevenLiuWen
faf18023f2 update 
Gradio Demo Example, Incremental Prefilling and VLMEvalKit Support
 2024-12-26 22:37:57 +08:00
Xingchao Liu
6036493d83 change module name to deepseek_vl2 2024-12-17 15:42:09 +08:00
Xingchao Liu
d527122a4d Initial commit 2024-12-13 20:38:59 +08:00