[visarga]

That's why it feels like installing a ML repo is like sudoku. You install everything and at the last step you realize your neural net uses FlashAttention2 which only works on NVIDIA compute version that is not deployed in your cloud VM and you need to start over from scratch.

[hskalin]

Sometimes I just change the version of the package in requirements to fit with others and pray that it works out (a few times it does)

[pjc50]

See the discussion on why sqlite insists on vendoring its build dependencies as far as possible and not using, say, CMake.

[austinjp]

This describes the day I wasted on Monday before I gave up and wrote some damn deterministic code instead of using some damn AI.

[nicman23]

honestly if the ml does not have a docker image - not compose no build an image- i do not even bother any more

[anthk]

Guix fixes that in the spot.