Remove ami pinning from scale-config.yml files (#6163)

At news year eve, we had an small CI outage. Queue started to grow due
to lack of capacity to create new linux instances. After investigating
the issue we noticed that this is due to the pinning of labels in the
`ami` tag of `scale-config.yml` and its variants. This is due to the
fact that for security reasons, Amazon removed the tag on its services,
so we could not resolve the AMI ID from the tag search.

The goal of this tag is to enable to migrate to a newer AMI type
runner-by-runner, so we can troubleshoot problems and avoid the issue of
being stuck in the migration because of a particular job that runs in a
particular instance. This was included with the concept of variants.

Now that the migration is complete, the correct approach is to
**REMOVE** these labels and rely on the labels that are pinned at
release/deploy time. They are safer, for many reasons, somo of them:

* The AMI id is pinned at release time, so if the label is not available
anymore, the instances are still able to be created;
* At the release time, we are immediately notified that the label is not
available anymore and we need to upgrade, plus it prevents moving
forward and deploying a broken state.
* We are able to test the changes (honestly, many times we don't, but
can and should)
* Minor version upgrades, that are potentially problematic, can be
rolled back faster;
* We have "hands on controls" and are aware of the releases, so we know
when a release is triggered and can monitor. Over have the change take
immediate effect when Amazon releases a newer minor version;
* Rolls forward is faster to a newer release and is guaranteed to be
complete;

So, to avoid outages similar to what we had, this action should be
taken.

This is on top of the following changes that correctly reflected the
pinning we're using to the release:
*
pytorch-labs/pytorch-gha-infra@ea8466e
- released on:
https://github.com/pytorch-labs/pytorch-gha-infra/actions/runs/12752938298
*
pytorch/ci-infra@f564bcf
- released on:
https://github.com/pytorch/ci-infra/actions/runs/12753299999

cc @zxiiro @malfet @atalman @seemethere @ZainRizvi

.github/lf-canary-scale-config.yml

@@ -37,157 +37,131 @@ runner_types:
     instance_type: m7i-flex.8xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.12xlarge:
     disk_size: 200
     instance_type: c5.12xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.10xlarge.avx2:
     disk_size: 200
     instance_type: m4.10xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.24xl.spr-metal:
     disk_size: 200
     instance_type: c7i.metal-24xl
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.16xlarge.spr:
     disk_size: 200
     instance_type: c7i.16xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.9xlarge.ephemeral:
     disk_size: 200
     instance_type: c5.9xlarge
     is_ephemeral: true
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.12xlarge.ephemeral:
     disk_size: 200
     instance_type: c5.12xlarge
     is_ephemeral: true
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.16xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g3.16xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.24xlarge:
     disk_size: 150
     instance_type: c5.24xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.24xlarge.ephemeral:
     disk_size: 150
     instance_type: c5.24xlarge
     is_ephemeral: true
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.2xlarge:
     disk_size: 150
     instance_type: c5.2xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.4xlarge:
     disk_size: 150
     instance_type: c5.4xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.4xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g3.4xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.8xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g3.8xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.g4dn.12xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g4dn.12xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.g4dn.metal.nvidia.gpu:
     disk_size: 150
     instance_type: g4dn.metal
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.g5.48xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g5.48xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.g5.12xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g5.12xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.g5.4xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g5.4xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.g6.4xlarge.experimental.nvidia.gpu:
     disk_size: 150
     instance_type: g6.4xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.large:
     disk_size: 15
     instance_type: c5.large
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.arm64.2xlarge:
     disk_size: 256
     instance_type: t4g.2xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-arm64
   lf.c.linux.arm64.m7g.4xlarge:
     disk_size: 256
     instance_type: m7g.4xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-arm64
   lf.c.linux.arm64.2xlarge.ephemeral:
     disk_size: 256
     instance_type: t4g.2xlarge
     is_ephemeral: true
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-arm64
   lf.c.linux.arm64.m7g.4xlarge.ephemeral:
     disk_size: 256
     instance_type: m7g.4xlarge
     is_ephemeral: true
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-arm64
   lf.c.linux.arm64.m7g.metal:
     disk_size: 256
     instance_type: m7g.metal
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-arm64
   lf.c.windows.g4dn.xlarge:
     disk_size: 256
     instance_type: g4dn.xlarge
@@ -228,22 +202,18 @@ runner_types:
     instance_type: r5.2xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.4xlarge.memory:
     disk_size: 300
     instance_type: r5.4xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.8xlarge.memory:
     disk_size: 400
     instance_type: r5.8xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.c.linux.12xlarge.memory:
     disk_size: 600
     instance_type: r5.12xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64

.github/lf-scale-config.yml

@@ -37,157 +37,131 @@ runner_types:
     instance_type: m7i-flex.8xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.12xlarge:
     disk_size: 200
     instance_type: c5.12xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.10xlarge.avx2:
     disk_size: 200
     instance_type: m4.10xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.24xl.spr-metal:
     disk_size: 200
     instance_type: c7i.metal-24xl
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.16xlarge.spr:
     disk_size: 200
     instance_type: c7i.16xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.9xlarge.ephemeral:
     disk_size: 200
     instance_type: c5.9xlarge
     is_ephemeral: true
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.12xlarge.ephemeral:
     disk_size: 200
     instance_type: c5.12xlarge
     is_ephemeral: true
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.16xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g3.16xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.24xlarge:
     disk_size: 150
     instance_type: c5.24xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.24xlarge.ephemeral:
     disk_size: 150
     instance_type: c5.24xlarge
     is_ephemeral: true
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.2xlarge:
     disk_size: 150
     instance_type: c5.2xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.4xlarge:
     disk_size: 150
     instance_type: c5.4xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.4xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g3.4xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.8xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g3.8xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.g4dn.12xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g4dn.12xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.g4dn.metal.nvidia.gpu:
     disk_size: 150
     instance_type: g4dn.metal
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.g5.48xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g5.48xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.g5.12xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g5.12xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.g5.4xlarge.nvidia.gpu:
     disk_size: 150
     instance_type: g5.4xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.g6.4xlarge.experimental.nvidia.gpu:
     disk_size: 150
     instance_type: g6.4xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.large:
     disk_size: 15
     instance_type: c5.large
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.arm64.2xlarge:
     disk_size: 256
     instance_type: t4g.2xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-arm64
   lf.linux.arm64.m7g.4xlarge:
     disk_size: 256
     instance_type: m7g.4xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-arm64
   lf.linux.arm64.2xlarge.ephemeral:
     disk_size: 256
     instance_type: t4g.2xlarge
     is_ephemeral: true
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-arm64
   lf.linux.arm64.m7g.4xlarge.ephemeral:
     disk_size: 256
     instance_type: m7g.4xlarge
     is_ephemeral: true
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-arm64
   lf.linux.arm64.m7g.metal:
     disk_size: 256
     instance_type: m7g.metal
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-arm64
   lf.windows.g4dn.xlarge:
     disk_size: 256
     instance_type: g4dn.xlarge
@@ -228,22 +202,18 @@ runner_types:
     instance_type: r5.2xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.4xlarge.memory:
     disk_size: 300
     instance_type: r5.4xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.8xlarge.memory:
     disk_size: 400
     instance_type: r5.8xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64
   lf.linux.12xlarge.memory:
     disk_size: 600
     instance_type: r5.12xlarge
     is_ephemeral: false
     os: linux
-    ami: al2023-ami-2023.6.202*-kernel-6.1-x86_64