try to use 48xlarge runners for llava-runner and eval_llama-mmlu

These jobs are timing out. I found big gaps in the timestamps of the logs even before the blame PR, which to me suggests swapping. Let's try bigger runner and see what happens on this PR.

Fixes #8180 (if it lands)

ghstack-source-id: 1648a66a3ed17701b2049481dffeb342d5c6f6c6
ghstack-comment-id: 2634545665
Pull Request resolved: #8181

.github/workflows/pull.yml

@@ -208,7 +208,7 @@ jobs:
     strategy:
       fail-fast: false
     with:
-      runner: linux.24xlarge
+      runner: linux.48xlarge
       docker-image: executorch-ubuntu-22.04-clang12
       submodules: 'true'
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
@@ -531,7 +531,7 @@ jobs:
     strategy:
       fail-fast: false
     with:
-      runner: linux.24xlarge
+      runner: linux.48xlarge
       docker-image: executorch-ubuntu-22.04-clang12
       submodules: 'true'
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}