Activity
Stars and mentions · Last 30 days, Oct 6 – Nov 4
Top repositories
wkentaro’s repositories ranked by new forks, as on trending.
Contributes to
Repositories outside wkentaro’s account where wkentaro opened or reviewed pull requests in the past 365 days.
Who noticed wkentaro
Everyone who starred or forked wkentaro’s repositories since the archive began in 2011.
Notable accounts
Ordered by the stars their own repositories have received.
Biggest fans
Accounts that starred the most of these repositories.
Breakout weeks
Each repository’s best week of new stars, with the release published around it.
Achievements
Awards earned by the repositories wkentaro owns. Select an award to embed its badge.
No awards yet
Repositories earn awards by reaching the top three in a completed trending day or week.
A repository earns an award for finishing first, second or third in a completed trending day or week, ranked by new stars, new forks or pull request authors. Awards follow a repository through renames and transfers and count toward its current owner. Weeks run Monday to Sunday, UTC.
Mentions
pip install 'osam[webgpu]' osam run sam3 --image dogs.jpg --text dog Speed on each device: wkentaro/osam
@Sanemavcil Thanks for sharing! The code is here: wkentaro/sam3-onnx wkentaro/osam
@decompte_macron let me finalize this soon osam#121
or just download ONNX models: huggingface.co Code and export scripts: wkentaro/sam3-onnx osam: wkentaro/osam The code is MIT. The weights keep Meta's SAM License.
On the M5, CoreML runs a text prompt 3.8x faster than the CPU, with identical masks. One text prompt, image already encoded: M5 CPU 1.43 s M5 CoreML 0.37 s RTX 3080 Ti 0.08 s Median of 5 runs, without model load. Full method: github.com/wkentaro/osam/blob/main/docs/benchmark… t.co