[Kernel/Quant] Remove AQLM (#22943)
Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
co-authored by
Wentao Ye
parent
3253ae765e
commit
4fc722eca4
@@ -154,15 +154,6 @@ void cutlass_mla_decode(torch::Tensor const& out, torch::Tensor const& q_nope,
|
||||
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,
|
||||
const torch::Tensor& scales,
|
||||
const std::vector<int64_t>& codebook_partition_sizes,
|
||||
const std::optional<torch::Tensor>& bias);
|
||||
|
||||
torch::Tensor aqlm_dequant(
|
||||
const torch::Tensor& codes, const torch::Tensor& codebooks,
|
||||
const std::vector<int64_t>& codebook_partition_sizes);
|
||||
|
||||
torch::Tensor awq_gemm(torch::Tensor _in_feats, torch::Tensor _kernel,
|
||||
torch::Tensor _scaling_factors, torch::Tensor _zeros,
|
||||
|
||||
Reference in New Issue
Block a user