blakkd

OK, so finally! A lower quant loads entirely, this was my fault. But, I still do have only a part of the RAM released after ollama server exit: ``` 0[0.6]...

Good guess! But unfortunately I already tried with `sudo sh -c 'echo 3 > /proc/sys/vm/drop_caches'` or the alternative you suggested but none of them does the trick here the used...

I tried getting help from Qwen3 32B, AM-thinking, and to finish dumbly following Gemini 2.5 pro instructions and: no clue, all end up concluding the only solution is to reboot....

I just noticed it's actually not specific to Kimi-Dev, but is happening with any model loaded in RAM instead of VRAM (here I tried with https://huggingface.co/WisdomShell/RewardAnything-8B-v1). I'll open a new...

Same issue here: ``` Continue: v0.9.182 (pre-release) VSCode: 1.91.1 Commit: f1e16e1e6214d7c44d078b1f0607b2388f29d729 Date: 2024-07-09T22:08:12.169Z Electron: 29.4.0 ElectronBuildId: 9728852 Chromium: 122.0.6261.156 Node.js: 20.9.0 V8: 12.2.281.27-electron.0 OS: Linux x64 6.5.0-41-generic ``` Some specific...

@rootsnet if you run into this, create a new playlist and add the tracks from the "for you" playlist to this new "regular" playlist. Then sync it instead ;)

https://mjmirza.github.io/Download-VSIX-From-Visual-Studio-Market-Place/ Source code is here https://github.com/mjmirza/Download-VSIX-From-Visual-Studio-Market-Place Hope this helps

If anyone feels like trying adding docker to the video group in `docker/gpu/docker-compose.yml` and see if this does the trick? https://github.com/remsky/Kokoro-FastAPI/pull/198/files#diff-6b65a4e9ffad3492f9e7ea20df64a768176ba404e3a98231f3879db6acbe9107

thanks!