[Kernel][Misc] register ops to prevent graph breaks (#6917)
Co-authored-by: Sage Moore <sage@neuralmagic.com>
This commit is contained in:
@@ -123,9 +123,17 @@ torch::Tensor gptq_marlin_repack(torch::Tensor& b_q_weight, torch::Tensor& perm,
|
||||
int64_t size_k, int64_t size_n,
|
||||
int64_t num_bits);
|
||||
|
||||
torch::Tensor gptq_marlin_repack_meta(torch::Tensor& b_q_weight,
|
||||
torch::Tensor& perm, c10::SymInt size_k,
|
||||
c10::SymInt size_n, int64_t num_bits);
|
||||
|
||||
torch::Tensor awq_marlin_repack(torch::Tensor& b_q_weight, int64_t size_k,
|
||||
int64_t size_n, int64_t num_bits);
|
||||
|
||||
torch::Tensor awq_marlin_repack_meta(torch::Tensor& b_q_weight,
|
||||
c10::SymInt size_k, c10::SymInt size_n,
|
||||
int64_t num_bits);
|
||||
|
||||
torch::Tensor ggml_dequantize(torch::Tensor W, int64_t type, int64_t m,
|
||||
int64_t n);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user