[Question]: How to use quantification and MInference together #181

Describe the issue

Thank you for your work. I’m quite curious about how the current approach (flexPrefill / triangle attention) can be used alongside quantization (fp8/int8/fp4) in vLLM/trt-llm, since quantization provides a very significant speedup in our scenario. Thank you! Huiqiang Jiang (@iofu728)