[None][fix] Honour producer ignored layers for fused MoE and any quant format - #17551

[None][fix] Honour producer ignored layers for fused MoE and any quant format#17551

joerowell wants to merge 3 commits into

NVIDIA:mainNVIDIA/TensorRT-LLM:mainfrom

joerowell:joerowell/fp8-ignored-layers-g-projjoerowell/TensorRT-LLM:joerowell/fp8-ignored-layers-g-projCopy head branch name to clipboard