TensorRT-LLM icon indicating copy to clipboard operation
TensorRT-LLM copied to clipboard
verified publisher icon NVIDIA

Fix baichuan smoothquant/INT8 KV cache build error

Open BasicCoder opened this issue 2 years ago • 0 comments

The baichuan convert script lacks scale_y_accum_quant, scale_w_quant_orig value saving.

BasicCoder avatar Nov 17 '23 03:11 BasicCoder