Add new-features section

[rahul-tuli]

This PR updates the main README.md to introduce a "New Features" section, improving visibility for recent major additions to LLM Compressor.

This section highlights:

• Axolotl Sparse Finetuning Integration (https://docs.axolotl.ai/docs/custom_integrations.html#llmcompressor)
• AutoAWQ Integration for low-bit weight quantization (AWQ Modifier #1177)
• Day 0 Llama 4 support and its use by Meta
  This helps users quickly understand the latest capabilities of the library.

[github-actions]

👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review.

Note: This is required to complete the testing suite, please only add the label once the PR is code complete and local testing has been performed.

[kylesayrs]

I would formalize the tone a little bit here.

Axolotl only supports one modifier atm (iirc),

I would also avoid using words like "our", since this is an open source community project.

- Meta utilized LLM Compressor to create the
+ See the FP8-quantized Llama-4-Maverick-17B-128E model created using LLM Compressor by the Meta AI team

[rahul-tuli]

I would formalize the tone a little bit here.

Axolotl only supports one modifier atm (iirc),

I would also avoid using words like "our", since this is an open source community project.

- Meta utilized LLM Compressor to create the
+ See the FP8-quantized Llama-4-Maverick-17B-128E model created using LLM Compressor by the Meta AI team

• I think the sentence reads okay;
• I removed our and linked out to compressed-tensors.
• w.r.t > Axolotl only supports one modifier atm (iirc),
  Which is all we need for Sparse Finetuning 👀