infini::ops::GptqMarlinRepack Member List

This is the complete list of members for infini::ops::GptqMarlinRepack, including all inherited members.

active_implementation_indices(Device::Type dev_type)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
active_implementation_indices(Device::Type dev_type)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
b_q_weight_metadata_	infini::ops::GptqMarlinRepack	protected
Call(const Handle &handle, const Config &config, const Args &... args)	infini::ops::Operator< GptqMarlinRepack >	static
Call(const Tensor tensor, const Args &... args)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
Call(const TensorLike &tensor, const Args &... args)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
Call(const Handle &handle, const Config &config, const Args &... args)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
Call(const Tensor tensor, const Args &... args)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
Call(const TensorLike &tensor, const Args &... args)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
clear_cache()	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
clear_cache()	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
config_ptr_	infini::ops::OperatorBase	protected
device_index_	infini::ops::GptqMarlinRepack	protected
device_type_	infini::ops::Operator< GptqMarlinRepack >	protectedstatic
GptqMarlinRepack(const Tensor b_q_weight, const Tensor perm, const int64_t size_k, const int64_t size_n, const int64_t num_bits, const bool is_a_8bit, Tensor out)	infini::ops::GptqMarlinRepack	inline
handle_ptr_	infini::ops::OperatorBase	protected
has_perm_	infini::ops::GptqMarlinRepack	protected
implementation_index_	infini::ops::Operator< GptqMarlinRepack >	protectedstatic
is_a_8bit_	infini::ops::GptqMarlinRepack	protected
Make(const Config &config, const Tensor tensor, Args &&... args)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
Make(const Tensor tensor, Args &&... args)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
Make(const Config &config, const std::vector< Tensor > tensors, Args &&... args)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
Make(const std::vector< Tensor > tensors, Args &&... args)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
Make(const Config &config, const Tensor tensor, Args &&... args)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
Make(const Tensor tensor, Args &&... args)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
Make(const Config &config, const std::vector< Tensor > tensors, Args &&... args)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
Make(const std::vector< Tensor > tensors, Args &&... args)	infini::ops::Operator< GptqMarlinRepack >	inlinestatic
num_bits_	infini::ops::GptqMarlinRepack	protected
operator()(const Tensor b_q_weight, const Tensor perm, const int64_t size_k, const int64_t size_n, const int64_t num_bits, const bool is_a_8bit, Tensor out) const =0	infini::ops::GptqMarlinRepack	pure virtual
Operator< GptqMarlinRepack >::operator()(const Handle &handle, const Args &... args)	infini::ops::Operator< GptqMarlinRepack >	inline
Operator< GptqMarlinRepack >::operator()(const Args &... args) const	infini::ops::Operator< GptqMarlinRepack >	inline
out_metadata_	infini::ops::GptqMarlinRepack	protected
pack_factor_	infini::ops::GptqMarlinRepack	protected
perm_metadata_	infini::ops::GptqMarlinRepack	protected
set_config(const Config &config)	infini::ops::OperatorBase	inline
set_config(const Config &config)	infini::ops::OperatorBase	inline
set_handle(const Handle &handle)	infini::ops::OperatorBase	inline
set_handle(const Handle &handle)	infini::ops::OperatorBase	inline
set_stream(void *stream)	infini::ops::OperatorBase	inline
set_stream(void *stream)	infini::ops::OperatorBase	inline
set_workspace(void *workspace)	infini::ops::OperatorBase	inline
set_workspace(void *workspace)	infini::ops::OperatorBase	inline
set_workspace_size_in_bytes(std::size_t workspace_size_in_bytes)	infini::ops::OperatorBase	inline
set_workspace_size_in_bytes(std::size_t workspace_size_in_bytes)	infini::ops::OperatorBase	inline
size_k_	infini::ops::GptqMarlinRepack	protected
size_n_	infini::ops::GptqMarlinRepack	protected
stream_	infini::ops::OperatorBase	protected
ValidateCallMetadata(const Tensor b_q_weight, const Tensor perm, const int64_t size_k, const int64_t size_n, const int64_t num_bits, const bool is_a_8bit, const Tensor out) const	infini::ops::GptqMarlinRepack	inlineprotected
workspace_	infini::ops::OperatorBase	protected
workspace_size_in_bytes() const	infini::ops::OperatorBase	inlinevirtual
workspace_size_in_bytes() const	infini::ops::OperatorBase	inlinevirtual
workspace_size_in_bytes_	infini::ops::OperatorBase	protected
~OperatorBase()=default	infini::ops::OperatorBase	virtual
~OperatorBase()=default	infini::ops::OperatorBase	virtual