fix(gpu): general fixes on indexes used in multi-gpu context

[pdroalves]

• fix a bug in which the wrong GPU may be queried for the max shared memory
• If multiple streams are running split through multiple GPUs, operations happening on a stream in GPU i should query GPU i about its max shared memory.
• also fixes wrong indexing at rust side

closes: https://github.com/zama-ai/tfhe-rs-internal/issues/901

PR content/description

Check-list:

• Tests for the changes have been added (for bug fixes / features)
• Docs have been added / updated (for bug fixes / features)
• Relevant issues are marked as resolved/closed, related issues are linked in the description
• Check for breaking changes (including serialization changes) and add them to commit message following the conventional commit specification

[github-actions]

⚠️ This PR contains unsigned commits. To get your PR merged, please sign those commits (git rebase --exec 'git commit -S --amend --no-edit -n' @{upstream}) and force push them to this branch (git push --force-with-lease).

If you're new to commit signing, there are different ways to set it up:

Sign commits with gpg

Follow the steps below to set up commit signing with gpg:

1. Generate a GPG key
2. Add the GPG key to your GitHub account
3. Configure git to use your GPG key for commit signing

Sign commits with ssh-agent

Follow the steps below to set up commit signing with ssh-agent:

1. Generate an SSH key and add it to ssh-agent
2. Add the SSH key to your GitHub account
3. Configure git to use your SSH key for commit signing

Sign commits with 1Password

You can also sign commits using 1Password, which lets you sign commits with biometrics without the signing key leaving the local 1Password process.

Learn how to use 1Password to sign your commits.

[pdroalves]

@agnesLertá maybe we could introduce a new test to cover this scenario. Wdyt?

[agnesLeroy]

Hey @pdroalves! Looks good to me thanks for the fix! Yes, we should definitely add a test for it. The thing is, for now only the long run tests are testing the use of a single GPU other than 0. What we could do is add long run tests with a set of classic PBS parameters maybe? Otherwise we could add signed & unsigned tests with a different FnExecutor, in the same fashion as I did for the long run tests. Wdyt? (see the executor here: tfhe/src/integer/gpu/server_key/radix/tests_long_run/mod.rs:34)

[agnesLeroy]

@pdroalves I saw the multi-gpu tests passed: maybe you want to merge the cudaSetDevice encapsulation first and then rebase this one on main before merging?

[pdroalves]

@agnesLeroy Actually that PR was based on this one.