gptq marlin quantization support for fused moe with lora (#30254)
Signed-off-by: Bhanu068 <voutharoja.bhanu06@gmail.com>
This commit is contained in:
@@ -860,4 +860,4 @@ torch::Tensor moe_wna16_marlin_gemm(
|
||||
|
||||
TORCH_LIBRARY_IMPL_EXPAND(TORCH_EXTENSION_NAME, CUDA, m) {
|
||||
m.impl("moe_wna16_marlin_gemm", &moe_wna16_marlin_gemm);
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user