[V1] Fully Transparent Implementation of CPU Offloading (#15354)
Signed-off-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
@@ -119,6 +119,8 @@ void advance_step_flashinfer(
|
||||
torch::Tensor& paged_kv_indices, torch::Tensor& paged_kv_indptr,
|
||||
torch::Tensor& paged_kv_last_page_len, torch::Tensor& block_table_bounds);
|
||||
|
||||
torch::Tensor get_cuda_view_from_cpu_tensor(torch::Tensor& cpu_tensor);
|
||||
|
||||
#ifndef USE_ROCM
|
||||
torch::Tensor aqlm_gemm(const torch::Tensor& input, const torch::Tensor& codes,
|
||||
const torch::Tensor& codebooks,
|
||||
|
||||
Reference in New Issue
Block a user