Support SqueezeLLM (#1326)

Co-authored-by: squeeze-ai-lab <squeezeailab.bair@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

csrc/quantization.cpp

@@ -7,9 +7,13 @@ torch::Tensor awq_gemm(
   torch::Tensor _zeros,
   int split_k_iters);
 
+void squeezellm_gemm(
+  torch::Tensor vec,
+  torch::Tensor mat,
+  torch::Tensor mul,
+  torch::Tensor lookup_table);
+
 PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
-  m.def(
-    "awq_gemm",
-    &awq_gemm,
-    "Quantized GEMM for AWQ");
+  m.def("awq_gemm", &awq_gemm, "Quantized GEMM for AWQ");
+  m.def("squeezellm_gemm", &squeezellm_gemm, "Quantized GEMM for SqueezeLLM");
 }