Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

merge master #115

Merged
merged 10 commits into from
Feb 23, 2024
Merged

merge master #115

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
96e0660
Merge pull request #70 from qingshui/paddlebox
qingshui Dec 1, 2023
5753cd0
fused_seqpool_cvm_with_conv support filter by threshold
mojingcj Dec 6, 2023
fda5286
Merge pull request #71 from mojingcj/paddlebox
jiaoxuewu Dec 6, 2023
b888ec3
add fill zero in fused_seqpool_cvm
yuandong1998 Dec 19, 2023
1ee052d
Merge pull request #74 from yuandong1998/paddlebox
qingshui Dec 20, 2023
08fbd50
add fused seq tensor && support transpose batch fc weight
Jan 4, 2024
61fa982
Merge pull request #75 from shang1017/query_seq_slots
qingshui Jan 8, 2024
61a9d60
Merge pull request #76 from qingshui/paddlebox
qingshui Jan 18, 2024
7acd059
fix fused query seq tensor compare case
Jan 24, 2024
5d50595
Merge pull request #77 from shang1017/fix_query_seq_slots
qingshui Jan 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions paddle/fluid/operators/fused/fused_seq_tensor_op.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,10 +47,10 @@ class FusedSeqTensorOp : public framework::OperatorWithKernel {
ad_slot_num, 0,
platform::errors::InvalidArgument(
"ad_slot_num [%ld] <= 0", ad_slot_num));
PADDLE_ENFORCE_LT(
PADDLE_ENFORCE_LE(
ad_slot_offset, slot_num - 1,
platform::errors::InvalidArgument(
"ad_slot_num [%ld] > slot_num - 1 [%ld]", ad_slot_offset, slot_num));
"ad_slot_num [%ld] > slot_num - 1 [%ld]", ad_slot_offset, slot_num));
PADDLE_ENFORCE_GE(
ad_slot_offset, 0,
platform::errors::InvalidArgument(
Expand Down
4 changes: 2 additions & 2 deletions paddle/fluid/operators/fused/fused_seq_tensor_op.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,8 +145,8 @@ __device__ void warpReduce(volatile T* cache, int tid) {

#define THREAD_PER_BLOCK 128
template <typename T>
__global__ void reduce_sum_max_length(const T* input, // 1
T* mask_output, // mask
__global__ void reduce_sum_max_length(const T* input,
T* mask_output,
const size_t batch_count,
const size_t ins_num,
const size_t slot_num,
Expand Down