[CT] Fix CT Config to honor fp8_inc KV cache dtype

[yiliu30]

Adapt the update in vllm-project/vllm#30141

        # llm-compressor mdls need to set cache_dtype to "fp8" manually.
        if getattr(quant_config, "kv_cache_scheme", None) is not None:
            kv_cache_dtype = "fp8"
            calculate_kv_scales = False
            if cache_config is not None:
                cache_config.cache_dtype = "fp8"
                cache_config.calculate_kv_scales = False

        self.kv_cache_torch_dtype = kv_cache_dtype_str_to_dtype(
            kv_cache_dtype, vllm_config.model_config
        )
        self.kv_cache_dtype = kv_cache_dtype

cc @hshen14 @thuang6 @lkk12014402

[Copilot]

Pull request overview

This PR fixes a configuration issue in the Compressed Tensors implementation for HPU (Habana Processing Unit) to properly handle the fp8_inc KV cache dtype instead of the default fp8 format.

Changes:

• Added a custom __init__ method to HPUCompressedTensorsConfig that overrides KV cache settings after parent initialization

---

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