Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Kernel] Fix deprecation function warnings squeezellm quant_cuda_kernel #6901

Merged
merged 1 commit into from
Jul 29, 2024
Merged

[Kernel] Fix deprecation function warnings squeezellm quant_cuda_kernel #6901

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions csrc/quantization/squeezellm/quant_cuda_kernel.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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>(),
Expand Down
Loading