Implement AWQ quantization support for LLaMA (#1032)

Co-authored-by: Robert Irvine <robert@seamlessml.com>
Co-authored-by: root <rirv938@gmail.com>
Co-authored-by: Casper <casperbh.96@gmail.com>
Co-authored-by: julian-q <julianhquevedo@gmail.com>

csrc/quantization.cpp

@@ -0,0 +1,15 @@
+#include <torch/extension.h>
+
+torch::Tensor awq_gemm(
+  torch::Tensor _in_feats,
+  torch::Tensor _kernel,
+  torch::Tensor _scaling_factors,
+  torch::Tensor _zeros,
+  int split_k_iters);
+
+PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
+  m.def(
+    "awq_gemm",
+    &awq_gemm,
+    "Quantized GEMM for AWQ");
+}