Making large AI models cheaper, faster and more accessible
COMMITS
November 13, 2025
Y
Merge pull request #6391 from hpcaitech/grpo-zero-bubble-rebase
YeAnbang committed
November 12, 2025
Y
November 11, 2025
Y
fix ci; specify flash-attn version
YeAnbang committed
November 10, 2025
Y
fix readme
YeAnbang committed
November 7, 2025
Y
Y
update readme
YeAnbang committed
P
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] committed
Y
all tests passed
YeAnbang committed
November 6, 2025
Y
cherry pick zero bubble RL
YeAnbang committed
July 21, 2025
Y
fix racing condition
YeAnbang committed
July 16, 2025
Y
add entropy
YeAnbang committed
July 14, 2025
Y
fix code evaluation
YeAnbang committed
July 9, 2025
Y
add code for zero-bubble implementation
YeAnbang committed
September 26, 2025
Y
update B200 info/img/benchmark (#6385)
Yanjia0 committed
September 3, 2025
S
Add new implementations of RL algorithms (#6383)
sglucas committed
August 26, 2025
W
[Ring Attention] Add more detailed references (#6294)
Wenxuan Tan committed
August 18, 2025
Y
Merge pull request #6378 from hpcaitech/grpo-latest-rebase-fix-resume
YeAnbang committed
August 15, 2025
H
Merge pull request #6376 from hpcaitech/grpo-latest-rebase-main
Hanks committed
Y
Y
fix dist log prob test
YeAnbang committed
August 14, 2025
P
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] committed
Y
H
Update timeout
Hanks committed
H
Update timeout
Hanks committed
August 13, 2025
H
reduce memory consumption
Hanks committed
H
reduce memory consumption
Hanks committed
August 12, 2025
Y
support resume training
YeAnbang committed
August 6, 2025
P
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] committed