- 26 Dec, 2025 1 commit
-
-
PanZezhong1725 authored
This reverts commit 25258029.
-
- 25 Dec, 2025 1 commit
-
-
qinyiqun authored
-
- 24 Dec, 2025 1 commit
-
-
baominghelly authored
-
- 23 Dec, 2025 1 commit
-
-
baominghelly authored
-
- 22 Dec, 2025 5 commits
-
-
wooway777 authored
-
wooway777 authored
-
PanZezhong authored
-
baominghelly authored
-
baominghelly authored
-
- 19 Dec, 2025 1 commit
-
-
pengcheng888 authored
-
- 18 Dec, 2025 1 commit
-
-
baominghelly authored
-
- 17 Dec, 2025 1 commit
-
-
wooway777 authored
-
- 16 Dec, 2025 1 commit
-
-
baominghelly authored
-
- 12 Dec, 2025 2 commits
- 10 Dec, 2025 5 commits
-
-
baominghelly authored
-
baominghelly authored
-
Ceng23333 authored
Signed-off-by:Ceng23333 <441651826@qq.com>
-
thatPepe authored
* issue/739 - support batched RoPE on Nvidia and CPU * issue/739 - metax, moore batched rope * issue/739 - adjust metax flags * issue/739 - added a rope module interface to forward inplace in output tensor
-
baominghelly authored
-
- 05 Dec, 2025 2 commits
- 03 Dec, 2025 1 commit
-
-
PanZezhong1725 authored
-
- 02 Dec, 2025 1 commit
-
-
pengcheng888 authored
-
- 01 Dec, 2025 2 commits
- 28 Nov, 2025 3 commits
- 24 Nov, 2025 1 commit
-
-
wooway777 authored
-
- 22 Nov, 2025 7 commits
- 21 Nov, 2025 3 commits
-
-
zhuyue authored
-
pengcheng888 authored
-
qinyiqun authored
* ISSUE/628 适配QY C610 GPU,增加编译选项,适配已有算子。添加bge类模型所需的算子,包括gelu,layer_norm,lp_norm(支持l1,l2 norm),relu,softmax,tanh。 --------- Co-authored-by:
xgqdut2016 <kenan_gewei@163.com> Co-authored-by:
xgqdut2016 <140036308+xgqdut2016@users.noreply.github.com>
-