Enum BuilderFlag 

#[repr(i32)]
pub enum BuilderFlag {
    kFP16 = 0,
    kINT8 = 1,
    kDEBUG = 2,
    kGPU_FALLBACK = 3,
    kREFIT = 4,
    kDISABLE_TIMING_CACHE = 5,
    kTF32 = 6,
    kSPARSE_WEIGHTS = 7,
    kSAFETY_SCOPE = 8,
    kOBEY_PRECISION_CONSTRAINTS = 9,
    kPREFER_PRECISION_CONSTRAINTS = 10,
    kDIRECT_IO = 11,
    kREJECT_EMPTY_ALGORITHMS = 12,
    kVERSION_COMPATIBLE = 13,
    kEXCLUDE_LEAN_RUNTIME = 14,
    kFP8 = 15,
    kERROR_ON_TIMING_CACHE_MISS = 16,
    kBF16 = 17,
    kDISABLE_COMPILATION_CACHE = 18,
    kSTRIP_PLAN = 19,
    kREFIT_IDENTICAL = 20,
    kWEIGHT_STREAMING = 21,
    kINT4 = 22,
    kREFIT_INDIVIDUAL = 23,
    kSTRICT_NANS = 24,
    kMONITOR_MEMORY = 25,
    kFP4 = 26,
    kEDITABLE_TIMING_CACHE = 27,
    kDISTRIBUTIVE_INDEPENDENCE = 28,
}

! ! \enum BuilderFlag ! ! \brief List of valid modes that the builder can enable when creating an engine from a network definition. ! ! \see IBuilderConfig::setFlags(), IBuilderConfig::getFlags() !

Variants

kFP16 = 0

! Enable FP16 layer selection, with FP32 fallback. ! Unsupported in TensorRT-RTX and deprecated in 1.0. Use strong typing instead.

kINT8 = 1

! Enable Int8 layer selection, with FP32 fallback with FP16 fallback if kFP16 also specified. ! Unsupported in TensorRT-RTX and deprecated in 1.0. Use strong typing instead.

kDEBUG = 2

! Enable debugging of layers via synchronizing after every layer.

kGPU_FALLBACK = 3

! Enable layers marked to execute on GPU if layer cannot execute on DLA.

kREFIT = 4

! Enable building a refittable engine.

kDISABLE_TIMING_CACHE = 5

! Disable reuse of timing information across identical layers.

kTF32 = 6

! Allow (but not require) computations on tensors of type DataType::kFLOAT to use TF32. ! TF32 computes inner products by rounding the inputs to 10-bit mantissas before ! multiplying, but accumulates the sum using 23-bit mantissas. Enabled by default.

kSPARSE_WEIGHTS = 7

! Allow the builder to examine weights and use optimized functions when weights have suitable sparsity.

kSAFETY_SCOPE = 8

! Change the allowed parameters in the EngineCapability::kSTANDARD flow to ! match the restrictions that EngineCapability::kSAFETY check against for DeviceType::kGPU ! and EngineCapability::kDLA_STANDALONE check against the DeviceType::kDLA case. This flag ! is forced to true if EngineCapability::kSAFETY at build time if it is unset. ! ! This flag is only supported in NVIDIA Drive(R) products. ! ! \deprecated Deprecated in TensorRT 10.16. ! In EngineCapability::kSTANDARD flow, safety restrictions are no longer supported. ! In EngineCapability::kSAFETY and EngineCapability::kDLA_STANDALONE flows, restrictions are enforced natively. ! This flag is retained for API compatibility but is ignored.

kOBEY_PRECISION_CONSTRAINTS = 9

! Require that layers execute in specified precisions. Build fails otherwise. ! Unsupported in TensorRT-RTX and deprecated in 1.0. Use strong typing instead.

kPREFER_PRECISION_CONSTRAINTS = 10

! Prefer that layers execute in specified precisions. ! Fall back (with warning) to another precision if build would otherwise fail. ! Unsupported in TensorRT-RTX and deprecated in 1.0. Use strong typing instead.

kDIRECT_IO = 11

! Require that no reformats be inserted between a layer and a network I/O tensor ! for which ITensor::setAllowedFormats was called. ! Build fails if a reformat is required for functional correctness. ! \deprecated Deprecated in TensorRT 10.7. Unneeded API.

kREJECT_EMPTY_ALGORITHMS = 12

! Fail if IAlgorithmSelector::selectAlgorithms returns an empty set of algorithms. ! \deprecated Deprecated in TensorRT 10.10. Unneeded API due to IAlgorithmSelector deprecation.

kVERSION_COMPATIBLE = 13

! Restrict to lean runtime operators to provide version forward compatibility ! for the plan. ! ! This flag is only supported by NVIDIA Volta and later GPUs. ! This flag is not supported in NVIDIA Drive(R) products.

kEXCLUDE_LEAN_RUNTIME = 14

! Exclude lean runtime from the plan when version forward compatability is enabled. ! By default, this flag is unset, so the lean runtime will be included in the plan. ! ! If BuilderFlag::kVERSION_COMPATIBLE is not set then the value of this flag will be ignored.

kFP8 = 15

! Enable plugins with FP8 input/output. ! This flag is not supported when HardwareCompatibilityLevel::kAMPERE_PLUS is enabled. ! \see HardwareCompatibilityLevel ! ! Unsupported in TensorRT-RTX and deprecated in 1.0. Use strong typing instead.

kERROR_ON_TIMING_CACHE_MISS = 16

! Emit error when a tactic being timed is not present in the timing cache. ! This flag has an effect only when IBuilderConfig has an associated ITimingCache.

kBF16 = 17

! Enable DataType::kBF16 layer selection, with FP32 fallback. ! This flag is only supported by NVIDIA Ampere and later GPUs. ! Unsupported in TensorRT-RTX and deprecated in 1.0. Use strong typing instead.

kDISABLE_COMPILATION_CACHE = 18

! Disable caching of JIT-compilation results during engine build. ! By default, JIT-compiled code will be serialized as part of the timing cache, which may significantly increase ! the cache size. Setting this flag prevents the code from being serialized. This flag has an effect only when ! BuilderFlag::DISABLE_TIMING_CACHE is not set.

kSTRIP_PLAN = 19

! Strip the refittable weights from the engine plan file.

kREFIT_IDENTICAL = 20

! Create a refittable engine under the assumption that the refit weights will be identical to those provided at ! build time. The resulting engine will have the same performance as a non-refittable one. All refittable weights ! can be refitted through the refit API, but if the refit weights are not identical to the build-time weights, ! behavior is undefined. When used alongside ‘kSTRIP_PLAN’, this flag will result in a small plan file for which ! weights are later supplied via refitting. This enables use of a single set of weights with different inference ! backends, or with TensorRT plans for multiple GPU architectures.

kWEIGHT_STREAMING = 21

! ! \brief Enable weight streaming for the current engine. ! ! Weight streaming from the host enables execution of models that do not fit ! in GPU memory by allowing TensorRT to intelligently stream network weights ! from the CPU DRAM. Please see ICudaEngine::getMinimumWeightStreamingBudget ! for the default memory budget when this flag is enabled. ! ! Enabling this feature changes the behavior of ! IRuntime::deserializeCudaEngine to allocate the entire network’s weights ! on the CPU DRAM instead of GPU memory. Then, ! ICudaEngine::createExecutionContext will determine the optimal split of ! weights between the CPU and GPU and place weights accordingly. ! ! Future TensorRT versions may enable this flag by default. ! ! \warning Enabling this flag may marginally increase build time. ! ! \warning Enabling this feature will significantly increase the latency of ! ICudaEngine::createExecutionContext. ! ! \see IRuntime::deserializeCudaEngine, ! ICudaEngine::getMinimumWeightStreamingBudget, ! ICudaEngine::setWeightStreamingBudget !

kINT4 = 22

! Enable plugins with INT4 input/output. ! Unsupported in TensorRT-RTX and deprecated in 1.0. Use strong typing instead.

kREFIT_INDIVIDUAL = 23

! Enable building a refittable engine and provide fine-grained control. This allows ! control over which weights are refittable or not using INetworkDefinition::markWeightsRefittable and ! INetworkDefinition::unmarkWeightsRefittable. By default, all weights are non-refittable when this flag is ! enabled. This flag cannot be used together with kREFIT or kREFIT_IDENTICAL.

kSTRICT_NANS = 24

! Disable floating-point optimizations: 0*x => 0, x-x => 0, or x/x => 1. These identities are ! not true when x is a NaN or Inf, and thus might hide propagation or generation of NaNs. This flag is typically ! used in combination with kSPARSE_WEIGHTS. ! There are three valid sparsity configurations. ! 1. Disable all sparsity. Both kSPARSE_WEIGHTS and kSTRICT_NANS are unset ! 2. Enable sparsity only where it does not affect propagation/generation of NaNs. Both kSPARSE_WEIGHTS and ! kSTRICT_NANS are set ! 3. Enable all sparsity. kSPARSE_WEIGHTS is set and kSTRICT_NANS is unset

kMONITOR_MEMORY = 25

! Enable memory monitor during build time.

kFP4 = 26

! Enable plugins with FP4 input/output. ! Unsupported in TensorRT-RTX and deprecated in 1.0. Use strong typing instead.

kEDITABLE_TIMING_CACHE = 27

! Enable editable timing cache.

kDISTRIBUTIVE_INDEPENDENCE = 28

! Enable distributive independence. ! When BuilderFlag::kDISTRIBUTIVE_INDEPENDENCE is set and a layer documents axis i of an output as a distributive ! axis, then the layer behaves exactly as if each evaluation across axis i was done using identical operations. ! The definition of distributive axis is as follows: ! For IMatrixMultiplyLayer: ! All axes that are not one of the vector or matrix dimensions are distributive axes. ! For layers that perform reduction: ! All non-reduction axes are distributive axes. ! For layers that perform einsum: ! Let n be the leftmost reduction axis. The axes to the left of n are distributive axes.

Implementations

impl BuilderFlag

pub const kWEIGHTLESS: BuilderFlag = BuilderFlag::kSTRIP_PLAN

Trait Implementations

impl Clone for BuilderFlag

fn clone(&self) -> BuilderFlag

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for BuilderFlag

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl From<BuilderFlag> for BuilderFlag

fn from(value: BuilderFlag) -> Self

Converts to this type from the input type.

impl Hash for BuilderFlag

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl Into<BuilderFlag> for BuilderFlag

fn into(self) -> BuilderFlag

Converts this type into the (usually inferred) input type.

impl Ord for BuilderFlag

fn cmp(&self, other: &BuilderFlag) -> Ordering

This method returns an Ordering between self and other.

fn max(self, other: Self) -> Self

where Self: Sized,

Compares and returns the maximum of two values.

fn min(self, other: Self) -> Self

where Self: Sized,

Compares and returns the minimum of two values.

fn clamp(self, min: Self, max: Self) -> Self

where Self: Sized,

Restrict a value to a certain interval.

impl PartialEq for BuilderFlag

fn eq(&self, other: &BuilderFlag) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl PartialOrd for BuilderFlag

fn partial_cmp(&self, other: &BuilderFlag) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

fn lt(&self, other: &Rhs) -> bool

Tests less than (for self and other) and is used by the < operator.

fn le(&self, other: &Rhs) -> bool

Tests less than or equal to (for self and other) and is used by the <= operator.

fn gt(&self, other: &Rhs) -> bool

Tests greater than (for self and other) and is used by the > operator.

fn ge(&self, other: &Rhs) -> bool

Tests greater than or equal to (for self and other) and is used by the >= operator.

impl Copy for BuilderFlag

impl Eq for BuilderFlag

impl StructuralPartialEq for BuilderFlag