Stars and mentions
Last 30 days, Oct 4 – Nov 2
Package downloads
Cumulative recorded downloads
Across 7 known packages in repositories vosen owns. Cumulative totals include recorded downloads before the selected range. Missing observations leave gaps; totals may be incomplete.
Top repositories
vosen’s repositories ranked by pull request authors, as on trending.
Contributes to
Repositories outside vosen’s account where vosen opened or reviewed pull requests in the past 365 days.
Who noticed vosen
Everyone who starred or forked vosen’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.
- Gold
- 01st place finishes
- Silver
- 12nd place finishes
- Bronze
- 03rd place finishes
- Awarded repositories
- 1Owned by vosen now
Repositories
Ordered by gold, then silver, then bronze.
- ZLUDABest: 2nd by stars, 1,083 stars010
Every award
Top-three finishes of these repositories in completed trending days and weeks, newest first.
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
ZLUDA: CUDA on non-NVIDIA GPUs (15k stars) What it does All text below is quoted directly from the project README. >CUDA on non-NVIDIA GPUs ZLUDA: - ZLUDA is a drop-in replacement for CUDA on non-NVIDIA GPUs. - ZLUDA allows running unmodified CUDA applications using non-NVIDIA GPUs with near-native performance - quick start (zluda.readthedocs.io) - Discord - news (vosen.github.io/ZLUDA) Repository vosen/ZLUDA Repository stats |Metric|Value| |:-|:-| |Stars|15,092| |Forks|956| |Last release|v6 (2026-06-29)| |Languages|Rust 95.2%, LLVM 4%, C++ 0.5%| |Contributors|24| |AI contributor accounts (Claude / Codex / Cursor / Copilot)|Copilot: 2| |AI co-authored commits|Copilot: 2| Main contributor |Field|Value| |:-|:-| |Name|Andrzej Janik| |GitHub|@vosen| |Commits to this repo|433 (top contributor)| |Followers|429| |Public repos|33| |On GitHub since|2011-11-19| ---------------------------------------------------------------------------------------- Discover the best GitHub repos without the endless scrolling. Get top repos organized by category (AI, DevOps, Databases & more), plus key takeaways from developers' most useful comments - all in one free, twice-weekly newsletter. 👉 Get the best repos & community insights - Free
// AI Infrastructure 7/10 ZLUDA keeps pushing drop-in CUDA on non-NVIDIA GPUs. If this matures it's one of the more meaningful cracks in GPU vendor lock-in we've seen. vosen/ZLUDA
CUDA対応appの実行先を、NVIDIA以外のGPUへ広げる試み。 ZLUDAは非NVIDIA GPUでCUDA appを動かすためのcompatibility layer。READMEはunmodified appを対象にしていますが、実際の対応hardware・softwareは公式quick startで確認してください。 vosen/ZLUDA
looks like zluda's still alive at least vosen/ZLUDA
Hatsune Miku v6 demo + rvc voice download Very convincing isn't it? You can grabbe my rvc model of miku v6 here : mediafire.com How to use the rvc - step 1 get this program : Releases · Tiger14n/RVC-GUI by clicking the blue text that says RVC-GUI-pkg-mp3fix.zip than extract that to a folder. Put the Miku rvc folder into the rvc gui / models folder. step 2: If your on a amd gpu get zluda: Releases · vosen/ZLUDA This pretty much fakes cuda which you need cuda to do anything rvc related. step 3: Launch the rvc program but double clicking the .bat file as if it was a exe file. Select a clear isolate vocal wave file potentially rendered from synthv. Select miku v6, set the f0 methoid to marvest, select the gpu option assuming you have a nvidia gpu otherwise cpu will work in most cases. Press convert. If the thing says it failed to load the voice just reselect miku v6. Than the program will re sample the voice to sound like miku :) Step 4: if the pitch sounds wrong just change the pitch on the pitch slider and re render the voice .