Skip to content

fix: delete using namespace std. #7766

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

Merged
tohtana merged 5 commits into from
Jan 10, 2026
Merged

fix: delete using namespace std. #7766

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a4affeb
fix: delete using namespace std.
nathon-lee Jan 8, 2026
7ec1a34
Update weight_prepacking.h
nathon-lee Jan 8, 2026
e81865b
Merge branch 'master' into fix_issue_7758
sfc-gh-truwase Jan 9, 2026
e1d9cd1
Merge branch 'master' into fix_issue_7758
tohtana Jan 9, 2026
d35435d
Merge branch 'master' into fix_issue_7758
tohtana Jan 10, 2026
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
10 changes: 4 additions & 6 deletions deepspeed/inference/v2/kernels/core_ops/cuda_linear/include/weight_prepacking.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,8 +12,6 @@
#include <stdio.h>
#include <vector>

using namespace std;

void Padding_8_FP6_To_8_Bytes(unsigned char Padded_FP6[],
unsigned char* FP6_Array) // padding 0 to the lowerest bit location
{
Expand Down Expand Up @@ -48,8 +46,8 @@ unsigned char Extract_4_Bits_From_2_PaddedFP6(
}

// dealing with 4 1*8 blocks of FP6
void Assign_32_FP6_To_4_Thread(vector<unsigned char> Seg_2bit[],
vector<unsigned char> Seg_4bit[],
void Assign_32_FP6_To_4_Thread(std::vector<unsigned char> Seg_2bit[],
std::vector<unsigned char> Seg_4bit[],
unsigned char* PTR_1,
unsigned char* PTR_2,
unsigned char* PTR_3,
Expand Down Expand Up @@ -154,8 +152,8 @@ void weight_matrix_prepacking(int* FP6Weights, size_t M, size_t K)
unsigned char* Weight_2bit = Weight_6bit;
unsigned char* Weight_4bit = Weight_6bit + M * K * 2 / 8;
//
vector<unsigned char> A_Segment_2bit[32];
vector<unsigned char> A_Segment_4bit[32];
std::vector<unsigned char> A_Segment_2bit[32];
std::vector<unsigned char> A_Segment_4bit[32];
//
size_t BytesPerRow = K * 6 / 8;
// Pass-1: (1) 2+4 split; (2) assign weights to 32 threads.
Expand Down