* Switch to punica-sgmv kernel from the Hub
This also switches (temporarily) to the tgi-nix/kernel-builder merge
branch, bumping up to CUDA 12.8 (same as non-Nix Torch).
* nix: client depends on aiohttp
This probably worked before the nixpkgs bump because a dependency
propagated aiohttp.
* Update to Torch 2.7.0
* Try to fix typer/click issue
* Pin click to fix incompatibility with typer
* Fix some test outputs with slight deviations
* Attempt again to sync with CI
* Mamba too
* Fixup mllama
Also switch to `unsloth/Llama-3.2-11B-Vision-Instruct` for testing
from the EU :).
* Update to `kernels` 0.2.1
The package was renamed from `hf-kernels` to `kernels`. The new version
also updates the lockfile format.
* Download kernels in `install-cuda` target
