[Bugfix] [ROCm] [Critical] fallback to regular abi for ROCm (#44648)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
This commit is contained in:
@@ -162,12 +162,13 @@ torch::stable::Tensor awq_dequantize(torch::stable::Tensor _kernel,
|
||||
// AllSpark ops: declarations are in the source files
|
||||
// (allspark_repack.cu and allspark_qgemm_w8a16.cu)
|
||||
|
||||
#endif
|
||||
|
||||
// CPU tensor -> CUDA UVA view (shared CUDA/ROCm)
|
||||
// TODO: Move this out once ROCm upgrade their torch to 2.11.
|
||||
// CPU tensor -> CUDA UVA view (shared CUDA)
|
||||
torch::stable::Tensor get_cuda_view_from_cpu_tensor(
|
||||
torch::stable::Tensor& cpu_tensor);
|
||||
|
||||
#endif
|
||||
|
||||
// Attention kernels (shared CUDA/ROCm)
|
||||
void merge_attn_states(
|
||||
torch::stable::Tensor& output,
|
||||
|
||||
Reference in New Issue
Block a user