From e8e28988f79b6993dc597d0ab1a2fc6e56d12b60 Mon Sep 17 00:00:00 2001
From: Tyler Michael Smith <tyler@neuralmagic.com>
Date: Mon, 29 Jul 2024 15:48:42 +0000
Subject: [PATCH] Fix deprecation function warnings squeezellm
 quant_cuda_kernel

---
 csrc/quantization/squeezellm/quant_cuda_kernel.cu | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/csrc/quantization/squeezellm/quant_cuda_kernel.cu b/csrc/quantization/squeezellm/quant_cuda_kernel.cu
index 40baac610869..714907428a1a 100644
--- a/csrc/quantization/squeezellm/quant_cuda_kernel.cu
+++ b/csrc/quantization/squeezellm/quant_cuda_kernel.cu
@@ -197,13 +197,13 @@ void squeezellm_gemm(torch::Tensor vec, torch::Tensor mat, torch::Tensor mul,
   const cudaStream_t stream = at::cuda::getCurrentCUDAStream();
   vllm::squeezellm::NUQ4MatMulKernel<<<blocks, threads, 0, stream>>>(
 #ifndef USE_ROCM
-      (half2*)vec.data<at::Half>(),
+      (half2*)vec.data_ptr<at::Half>(),
 #else
       (__half2*)vec.data_ptr<at::Half>(),
 #endif
       mat.data_ptr<int>(),
 #ifndef USE_ROCM
-      (half2*)mul.data<at::Half>(), (__half*)lookup_table.data<at::Half>(),
+      (half2*)mul.data<at::Half>(), (__half*)lookup_table.data_ptr<at::Half>(),
 #else
       (float2*)mul.data_ptr<float>(),
       (__half*)lookup_table.data_ptr<at::Half>(),