Temp fix for sporadic CUDA operation not permitted errors with nvidia

For managing the sessions per AI capability + model ID in a way that is compatible with existing broadcast session code

This should no longer be needed because the field is deprecated

This commit adds detailed instructions for setting up an
orchestrator on the AI Subnet.

This commit adds detailed instructions for setting up an
broadcaster on the AI Subnet.

This commit refines the AI Subnet documentation and introduces instructions for
utilizing the prebuilt AI Subnet binaries.

This commit improves the AI subnet documentation by adding some missing
steps and improved unclear steps. Special thanks to @Pon-node for
walking through the documentation as I could code along and improve it.

Co-authored-by: Pon <[email protected]>

This commit fixes a broken huggingface documentation link.

Co-authored-by: papabear99 <[email protected]>

This commit fixes the broken `dl_checkpoints.sh` run command found in
the documentation.

Co-authored-by: papabear99 <[email protected]>

This commit refines the AI subnet documentation to address ambiguities
and inaccuracies identified during our initial pilot with **pre-alpha**
participants. The improvements aim to provide clearer instructions and
correct information for a smoother user experience.

This commit explaines the parameters found in the `aiModels.json` file.

…chestrator

This commit introduces comprehensive instructions for setting up the AI
Subnet Orchestrator for on-chain operation. It includes both binary and
Docker setup methods.

This commit restructures the AI on-chain instructions to make them
easier to follow.

This commit applies some small syntax changes to the ai documentation to
improve readability.

docs(ai): improve ai docs syntax

This commit adds some documentation on how people can **opt-in** to send
us data about their AI Subnet Orchestrator.

This update modifies the volume mount for the promptail docker container
to remove the ai_subnet_promtail.yml file, addressing issues reported by
several users with the previous promtail docker configuration.

This commit ensures that people use named docker containers. This will
help us monitor their metrics when they decide to share them.

This commit improves the description of the `warm` configuration value
and add the `ticketEV` flag to the Livepeer command line arguments to
prevent the `too many values` error from occuring. This error is thrown
because the current software does not allow sending more than 150
tickets in one batch.

This commit ensures it is clear that the redeemer is not recommended
when setting up a AI subnet orchestrator. It also explains that the
`pricePerUnit` flag is not needed for the AI subnet orchestrator.

This commit ensures that users know which output to expect when they run
the commands in the documentation:

This commit adds the initial draft for the AI subnet onboarding documentation.

This commit introduces two new AI-specific issue templates, aiming to streamline
the routing of AI subnet-related issues and feature requests to the appropriate team.

This commit adds a pull request labeler action that automatically
attaches the `ai` label when a pull request is created to the `ai-video`
branch.

This commit ensures that the main branch issue templates are put above
the AI related issue templates.

This commmit adds a https://github.com/actions/labeler configuration
file so that all PRs on the `ai-video` branch will be correctly labeled
with the `ai` label.

This commit fixed the labels that were specified in the Issue Templates
to the one found in the repository.

* feat(ai): add pipelines optimization flags

This commit adds a new `OptimizationFlags` field to the `aiModels`
config so that users can forward optimization environment variables to
the [ai-worker]([email protected]:livepeer/ai-worker.git) for more
information see livepeer/ai-worker#61.

* chore: update ai-worker to latest commit

This commit ensures that the https://github.com/livepeer/ai-worker
dependency is on the latest commit that includes the new optimization
flags feature (see livepeer/ai-worker#61).

* refactor: improve OptFlags logging

This commit ensures that the `optimzation flag not supported` warning
is shown for each model that is not loaded warm.

This commit adds a new section explaining the new `optimization_flags` that were enabled
#3013.

This commit temporary changes the push branch of the `build.yml` to the
`ai-video` branch since the `ai-video` branch has conflicts with the
`master` branch preventing the containers to be build.

This commit temporary changes the push branch of the `docker.yml` to the
`ai-video` branch since the `ai-video` branch has conflicts with the
`master` branch preventing the containers to be build.

This commit gets rid of the Pull request labeler configuration file
warning.

This commit flushes the data in the image writer to ensure that all data gets written to the PNG.

This commit ensures that the labeler action also runs on a
'pull_request_target' to ensure pull requests from forks are correctly
labeled.

This commit ensures that all AI related issues and feature requests are
assigned to the AI team.

* feat(ai): enable AI orchestrator discovery

This commit incorporates the AIServiceRegistry contract address,
superseding the conventional ServiceRegistry contract address. This
strategic alteration streamlines the discovery process of AI Orchestrators
within the AI Subnet, thereby bolstering network accessibility and interaction.
While this approach serves as a swift workaround to enable the feature without
extensive code modification, it's important to note that it may disrupt the
existing transcoding discovery mechanism. We have to fix this if we want to
merge the two networks in the future.

* docs(ai): improve discovery documentation

This commit ensures that people are aware that they have to interact
with the `AIServiceRegistry` using their main Orch wallet.

* fix: fix 'AIServiceRegistry' devnet and testnet issue

This commit ensure that the hardcoded `AIServiceRegistry` contract
doesn't break the go-livepeer binary on local devnets or testnets.

This commit adds extra devtool input arguments allowing developers to
spin up multiple Os on the ETH devnet.

This commit improves the devtool documentation and adds a helpful script
if developers want to create multiple Os at the same time.

This commit logs the advertised capabilities and price on startup if users have their logging verbosity level set to 6 or higher.

This commit ensures that an error is thrown when users don't specify
the 'aiModels' flag but have the 'aiWorker' flag set.

* fix(ai): improve selection algorithm

This commit modifies the selection algorithm to continue retrying for a
duration of one second instead of stopping after four attempts. This
change addresses issues encountered with the current algorithm's
performance in environments with 15 nodes on the network, ensuring more
robust and reliable operation until further optimizations can be
implemented.

* refactor(ai): enhance selection algorithm retry logic

This commit replaces the time-based for-loop in the selection
algorithm's retry logic with a more context-aware approach.