Add: Support for Sparse24Bitmask Compressed Models

[rahul-tuli]

This PR adds support for models compressed using Sparse24BitMask Compressor to cutlass 2:4 Kernels

• Adds support for compressed cases
• Introduces a new BitmaskShapeParameter

This diff was manually tested on:

• nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-chnl_wts_per_tok_dyn_act_fp8-BitM
• nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-chnl_wts_per_tok_dyn_act_int8-BitM
• nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-tensor_wts_tensor_act_fp8-BitM
• nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-tensor_wts_tensor_act_int8-BitM
• nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-tensor_wts_per_tok_dyn_act_fp8-BitM
• nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-tensor_wts_per_tok_dyn_act_int8-BitM
• nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-chnl_wts_tensor_act_fp8-BitM
• nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-chnl_wts_tensor_act_int8-BitM

Also added unit tests for the compressed cases!!

Needs the following compressed-tensors PR to land:

• SparseBitmask hacks for fp8 compressed-tensors#222

Notion Doc: https://www.notion.so/SparseBitMask-24-work-15e863ebf65c80dcbc70e6317d552987

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.
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 do one of these:

• Add ready label to the PR
• Enable auto-merge.

🚀

[dsikka]

Very nice. I think we'll create a new PR off of main once the initial PR lands.