Integrate Marlin Kernels for Int4 GPTQ inference (#2497)

Co-authored-by: Robert Shaw <114415538+rib-2@users.noreply.github.com>
Co-authored-by: alexm <alexm@neuralmagic.com>

csrc/pybind.cpp

@@ -52,11 +52,13 @@ PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
     &rotary_embedding,
     "Apply GPT-NeoX or GPT-J style rotary embedding to query and key");
 
-  // Quantization ops
+// Quantization ops
 #ifndef USE_ROCM
   ops.def("awq_gemm", &awq_gemm, "Quantized GEMM for AWQ");
+  ops.def("marlin_gemm", &marlin_gemm, "Marlin Optimized Quantized GEMM for GPTQ");
   ops.def("awq_dequantize", &awq_dequantize, "Dequantization for AWQ");
 #endif
+ 
   ops.def("gptq_gemm", &gptq_gemm, "Quantized GEMM for GPTQ");
   ops.def("gptq_shuffle", &gptq_shuffle, "Post processing for GPTQ");
   ops.def("squeezellm_gemm", &squeezellm_gemm, "Quantized GEMM for SqueezeLLM");