Roman Polyanovsky

I'm seeing similar results, and I _think_ I'm sampling it correctly: `ffmpeg -i 'video.avi' -vf format=rgb24 out_%05d.png` anything obvious wrong with those args?

I am seeing the same issue in postgres, also with a similar merge into query.

Hi Louie, sorry for the delayed response. Just to note: I am on an Asus Zenbook S14 - an Intel Lunar Lake laptop. xpu-smi does not seem to work: ```...

The container is running with `-it` so usually killing the entrypoint in that terminal stops the container as well. I've also tried `docker kill` which says its not running: `Error...

Is there at least some way to manually free the memory because otherwise I have to restart my entire computer after running a single inference task every single time.

Yes, there is a point during step 2, where the model is "moved" to the "GPU", and in `top` the memory usage of python process decreases, but memory usage overall...

I want to add that I have also observed this without docker, just running using the ipex pip packages, and using completely different models (microsoft Florence-2-large, using the [sample code...

I am seeing a similar issue. Set everything up from scratch as of time of writing. Running `mlc_llm package` same as above. ``` [100%] Building CXX object CMakeFiles/tvm4j_runtime_packed.dir/home/roman/Projects/mlc-llm/3rdparty/tvm/jvm/native/src/main/native/org_apache_tvm_native_c_api.cc.o In file...

I don't see an option to boot the LTS kernel from the live iso (maybe I'm misunderstanding your suggestion). I only see 6.12.11 which never makes it to tty. Edit:...