gptq marlin quantization support for fused moe with lora (#30254)

Signed-off-by: Bhanu068 <voutharoja.bhanu06@gmail.com>
This commit is contained in:
Bhanu Prakash Voutharoja
2025-12-12 02:27:22 +00:00
committed by GitHub
parent f355ad5412
commit 6a6fc41c79
3 changed files with 146 additions and 2 deletions
+1 -1
View File
@@ -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);
}
}