Block matmul and kv_cache in dynamic quantization

[HolyFalafel]

Currently disabling matmul and kv_cache in dynamic quantization mode

[Copilot]

Pull request overview

This PR configures dynamic quantization to exclude specific matrix multiplication and key-value cache operations from quantization. The changes prevent quantization of attention mechanism components that may be sensitive to quantization effects.

Key Changes:

• Added a blocklist to the quantization configuration
• Excluded Matmul and KVCache operation types from quantization
• Excluded specific attention-related operations (matmul_qk, matmul_av, k_cache, v_cache) by name

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[github-actions]

✅ CI Passed

All checks passed successfully against the following vllm commit:
3a7751485b71ce5ef927e4aa03b28602cb90811c

[xuechendi]

Is it for performance reason?

[HolyFalafel]

Is it for performance reason?

No, dynamic quantization for KVCache+Matmul is a new feature that we don't want to enable by default

[github-actions]

✅ CI Passed

All checks passed successfully against the following vllm commit:
899e2ef558e7345b99bc0d53c2e1c60ffdca7470

[github-actions]

🚧 CI Blocked

The main CI workflow was not started for the following reason:

Your branch is behind the base branch. Please merge or rebase to get the latest changes.