DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
COMMITS
/ docs/_tutorials/inference-tutorial.md February 26, 2025
L
Improve inference tutorial docs (#7083)
Logan Adams committed
February 5, 2025
O
Update GH org references (#6998)
Olatunji Ruwase committed
February 2, 2024
January 31, 2024
M
update inference pages to point to FastGen (#5029)
Michael Wyatt committed
July 13, 2023
L
Fix docs for checkpoints (#3955)
Logan Adams committed
May 12, 2023
D
fix typo with docs/ (#3523)
digger-yu committed
March 17, 2023
S
Fix Broken Links (#3048)
Satpal Singh Rathore committed
February 15, 2023
A
Refactor DS inference API. No longer need replace_method. (#2831)
Ammar Ahmad Awan committed
March 11, 2022
C
Website posts and tutorial improvements (#1799)
Cheng Li committed
February 3, 2022
R
Fix the tensor-slicing with multi-GPU inference and kernel-injection (#1724)
Reza Yazdani committed
January 19, 2022
R
Fix inference api & add more description on inference engine tutorial (#1711)
Reza Yazdani committed
January 3, 2022
M
Various small documentation text improvements (#1665)
Manuel R. Ciosici committed
October 1, 2021
A
Improve inference documentation (#1421)
Alex Hedges committed
June 15, 2021
H
Fix bugs in the tutorial documentation (#1157)
Hyunwoong Ko committed
May 27, 2021
R
fix links for inference tutorial (#1113)
Reza Yazdani committed
May 24, 2021
R
fix inference titles and add MoQ pictures (#1092)
Reza Yazdani committed
R
Quantization + inference release (#1091)
Reza Yazdani committed