Consolidate Llama model usage in tests

[hmellor]

Use meta-llama/Llama-3.2-1B-Instruct for as many models as possible which used larger/older/base variations of Llama.

N.B.

• LoRA tests could not have their models updated due to having adapters dependent on Llama 2
• Tool use needed the 3B model
• Spec decoding tests need a compatible draft and the current meta-llama/Llama-2-7b-chat-hf + JackFram/llama-68m is faster than Llama 3.2 3B + 1B
• It's worth noting that neuralmagic/Meta-Llama-3-8B-Instruct-FP8 (old) has static per-tensor activations while neuralmagic/Llama-3.2-1B-Instruct-FP8-dynamic (new) is dynamic per token. Therefore, what we're testing in this test has changed slightly

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[tlrmchlsmth]

Thanks for going through this!

[DarkLight1337]

There are persistent speculative decoding failures but they are not related to this PR. Merging.