Enum Class WeightGemmBackend

java.lang.Object

java.lang.Enum<WeightGemmBackend>

smile.llm.quant.WeightGemmBackend

All Implemented Interfaces:

Serializable, Comparable<WeightGemmBackend>, Constable

public enum WeightGemmBackend
extends Enum<WeightGemmBackend>

Weight GEMM backend selected from checkpoint format and GPU capability.

Policy (locked):

• Dense → DENSE
• Native FP8 on sm_90+ → FP8
• Native NVFP4 on sm_100+ → NVFP4
• GPTQ/AWQ on Ampere/Ada (8.0–8.9) → MARLIN
• GPTQ/AWQ on Hopper/Blackwell → fail fast (no Marlin)

Nested Class Summary

Nested classes/interfaces inherited from class Enum

Enum.EnumDesc<E>

Enum Constant Summary

Enum Constants

Enum Constant	Description
DENSE	Dense BF16/FP16 GEMM.
FP8	Native FP8 weight GEMM (Hopper+).
MARLIN	Marlin INT4 failover (Ampere/Ada).
NVFP4	Native NVFP4 weight GEMM (Blackwell+).

Method Summary

Modifier and Type	Method	Description
static int[]	computeCapability(Device device)	Returns {major, minor} for device, or {0,0} on CPU.
boolean	isFailover()	Returns whether this backend is the Ampere/Ada INT4 failover.
boolean	isPrimary()	Returns whether this is a primary native low-precision path.
static WeightGemmBackend	select(Device device, QuantFormat format)	Selects the weight GEMM backend.
static WeightGemmBackend	valueOf(String name)	Returns the enum constant of this class with the specified name.
static WeightGemmBackend[]	values()	Returns an array containing the constants of this enum class, in the order they are declared.

Methods inherited from class Enum

clone, compareTo, describeConstable, equals, finalize, getDeclaringClass, hashCode, name, ordinal, toString, valueOf

Methods inherited from class Object

getClass, notify, notifyAll, wait, wait, wait

Enum Constant Details

DENSE

public static final WeightGemmBackend DENSE

Dense BF16/FP16 GEMM.

FP8

public static final WeightGemmBackend FP8

Native FP8 weight GEMM (Hopper+).

NVFP4

public static final WeightGemmBackend NVFP4

Native NVFP4 weight GEMM (Blackwell+).

MARLIN

public static final WeightGemmBackend MARLIN

Marlin INT4 failover (Ampere/Ada).

Method Details

values

public static WeightGemmBackend[] values()

Returns an array containing the constants of this enum class, in the order they are declared.

Returns:

an array containing the constants of this enum class, in the order they are declared

valueOf

public static WeightGemmBackend valueOf(String name)

Returns the enum constant of this class with the specified name. The string must match exactly an identifier used to declare an enum constant in this class. (Extraneous whitespace characters are not permitted.)

Parameters:

name - the name of the enum constant to be returned.

Returns:

the enum constant with the specified name

Throws:

IllegalArgumentException - if this enum class has no constant with the specified name

NullPointerException - if the argument is null

select

public static WeightGemmBackend select(Device device,
 QuantFormat format)

Selects the weight GEMM backend.

Parameters:

device - CUDA (or CPU) device that will run inference.

format - checkpoint quantization format.

Returns:

the backend to use.

Throws:

IllegalStateException - on unsupported format/GPU combinations.

computeCapability

public static int[] computeCapability(Device device)

Returns {major, minor} for device, or {0,0} on CPU.

Parameters:

device - compute device.

Returns:

CUDA compute capability major/minor.

isFailover

public boolean isFailover()

Returns whether this backend is the Ampere/Ada INT4 failover.

Returns:

true when this backend is the Ampere/Ada INT4 failover.

isPrimary

public boolean isPrimary()

Returns whether this is a primary native low-precision path.

Returns:

true when this is a primary native low-precision path.