Skip to content

feat: add onerec 3b performance optimization and support old model. #1286

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
DragonFive merged 4 commits into from
Apr 20, 2026
Merged

feat: add onerec 3b performance optimization and support old model. #1286

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
bdb079c
bugfix: align onerec 3b npu runtime with xllm_rec.
DragonFive Apr 15, 2026
b11c793
bugfix: gate onerec legacy and 3b scaling paths.
DragonFive Apr 15, 2026
5594aa2
bugfix: address onerec review feedback.
DragonFive Apr 15, 2026
fd31036
bugfix: address remaining onerec review feedback.
DragonFive Apr 16, 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
2 changes: 1 addition & 1 deletion third_party/xllm_atb_layers
Open in desktop
Submodule xllm_atb_layers updated from d6aa21 to 96d3de
1 change: 1 addition & 0 deletions xllm/core/framework/tokenizer/rec_tokenizer.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ limitations under the License.
#include <string_view>
#include <vector>

#include "common/types.h"
#include "tokenizer.h"
#include "tokenizer_args.h"
#include "util/slice.h"
Expand Down
Loading
Loading