List of all items

Structs

• generation::LogitsProcessor
• models::based::Config
• models::based::LinearAttentionConfig
• models::based::LinearAttentionFeatureMapConfig
• models::based::Model
• models::based::SlidingWindowAttentionConfig
• models::beit::BeitVisionTransformer
• models::bert::BertEncoder
• models::bert::BertForMaskedLM
• models::bert::BertLMPredictionHead
• models::bert::BertLayer
• models::bert::BertModel
• models::bert::BertOnlyMLMHead
• models::bert::Config
• models::bigcode::Config
• models::bigcode::GPTBigCode
• models::blip::BlipForConditionalGeneration
• models::blip::Config
• models::blip::VisionConfig
• models::blip::VisionModel
• models::blip_text::Config
• models::blip_text::TextLMHeadModel
• models::blip_text::TextPooler
• models::chatglm::Config
• models::chatglm::Model
• models::chinese_clip::ChineseClipConfig
• models::chinese_clip::ChineseClipModel
• models::chinese_clip::text_model::ChineseClipTextConfig
• models::chinese_clip::text_model::ChineseClipTextEmbeddings
• models::chinese_clip::text_model::ChineseClipTextTransformer
• models::chinese_clip::vision_model::ChineseClipVisionConfig
• models::chinese_clip::vision_model::ChineseClipVisionEmbeddings
• models::chinese_clip::vision_model::ChineseClipVisionEncoder
• models::chinese_clip::vision_model::ChineseClipVisionTransformer
• models::clip::ClipConfig
• models::clip::ClipModel
• models::clip::text_model::ClipEncoder
• models::clip::text_model::ClipTextConfig
• models::clip::text_model::ClipTextTransformer
• models::clip::vision_model::ClipVisionConfig
• models::clip::vision_model::ClipVisionTransformer
• models::codegeex4_9b::Config
• models::codegeex4_9b::Model
• models::colpali::Model
• models::convnext::Config
• models::dac::Config
• models::dac::Decoder
• models::dac::DecoderBlock
• models::dac::Encoder
• models::dac::EncoderBlock
• models::dac::Model
• models::dac::ResidualUnit
• models::dac::ResidualVectorQuantizer
• models::dac::Snake1d
• models::dac::VectorQuantizer
• models::depth_anything_v2::DPTHead
• models::depth_anything_v2::DepthAnythingV2
• models::depth_anything_v2::DepthAnythingV2Config
• models::depth_anything_v2::FeatureFusionBlock
• models::depth_anything_v2::ResidualConvUnit
• models::depth_anything_v2::Scratch
• models::dinov2::DinoVisionTransformer
• models::dinov2reg4::DinoVisionTransformer
• models::distilbert::Config
• models::distilbert::DistilBertModel
• models::efficientnet::EfficientNet
• models::efficientnet::MBConvConfig
• models::efficientvit::Config
• models::encodec::Config
• models::encodec::Decoder
• models::encodec::EncodecConv1d
• models::encodec::EncodecConvTranspose1d
• models::encodec::EncodecLSTM
• models::encodec::EncodecResnetBlock
• models::encodec::Encoder
• models::encodec::EuclideanCodebook
• models::encodec::Model
• models::encodec::ResidualVectorQuantizer
• models::encodec::VectorQuantization
• models::eva2::EVA2VisionTransformer
• models::falcon::Config
• models::falcon::Falcon
• models::fastvit::Config
• models::flux::autoencoder::AutoEncoder
• models::flux::autoencoder::Config
• models::flux::autoencoder::Decoder
• models::flux::autoencoder::DiagonalGaussian
• models::flux::autoencoder::Encoder
• models::flux::model::Config
• models::flux::model::DoubleStreamBlock
• models::flux::model::EmbedNd
• models::flux::model::Flux
• models::flux::model::LastLayer
• models::flux::model::MlpEmbedder
• models::flux::model::QkNorm
• models::flux::model::SelfAttention
• models::flux::model::SingleStreamBlock
• models::flux::quantized_model::DoubleStreamBlock
• models::flux::quantized_model::Flux
• models::flux::quantized_model::LastLayer
• models::flux::quantized_model::MlpEmbedder
• models::flux::quantized_model::QkNorm
• models::flux::quantized_model::SelfAttention
• models::flux::quantized_model::SingleStreamBlock
• models::flux::sampling::State
• models::gemma2::Config
• models::gemma2::Model
• models::gemma::Config
• models::gemma::Model
• models::glm4::Config
• models::glm4::Model
• models::granite::Cache
• models::granite::Config
• models::granite::Granite
• models::granite::GraniteConfig
• models::granite::GraniteRopeConfig
• models::hiera::Config
• models::jina_bert::BertModel
• models::jina_bert::Config
• models::llama2_c::Cache
• models::llama2_c::Config
• models::llama2_c::Llama
• models::llama2_c_weights::TransformerWeights
• models::llama::Cache
• models::llama::Config
• models::llama::Llama
• models::llama::Llama3RopeConfig
• models::llama::LlamaConfig
• models::llava::ClipVisionTower
• models::llava::IdentityMap
• models::llava::LLaVA
• models::llava::MMProjector
• models::llava::config::HFGenerationConfig
• models::llava::config::HFLLaVAConfig
• models::llava::config::HFLLaVATextConfig
• models::llava::config::HFLLaVAVisionConfig
• models::llava::config::HFPreProcessorConfig
• models::llava::config::LLaVAConfig
• models::mamba::Config
• models::mamba::MambaBlock
• models::mamba::Model
• models::mamba::ResidualBlock
• models::mamba::State
• models::marian::Config
• models::marian::Decoder
• models::marian::Encoder
• models::marian::MTModel
• models::metavoice::adapters::FlattenedInterleavedEncodec2Codebook
• models::metavoice::adapters::TiltedEncodec
• models::metavoice::gpt::Config
• models::metavoice::gpt::Model
• models::metavoice::speaker_encoder::Config
• models::metavoice::speaker_encoder::Model
• models::metavoice::tokenizers::BPE
• models::metavoice::transformer::Config
• models::metavoice::transformer::Model
• models::mimi::conv::ConvDownsample1d
• models::mimi::conv::ConvTrUpsample1d
• models::mimi::conv::NormConv1d
• models::mimi::conv::NormConvTranspose1d
• models::mimi::conv::StreamableConv1d
• models::mimi::conv::StreamableConvTranspose1d
• models::mimi::encodec::Config
• models::mimi::encodec::Encodec
• models::mimi::quantization::EuclideanCodebook
• models::mimi::quantization::ResidualVectorQuantization
• models::mimi::quantization::ResidualVectorQuantizer
• models::mimi::quantization::SplitResidualVectorQuantizer
• models::mimi::quantization::VectorQuantization
• models::mimi::seanet::Config
• models::mimi::seanet::SeaNetDecoder
• models::mimi::seanet::SeaNetEncoder
• models::mimi::seanet::SeaNetResnetBlock
• models::mimi::transformer::Config
• models::mimi::transformer::LayerScale
• models::mimi::transformer::ProjectedTransformer
• models::mimi::transformer::RmsNorm
• models::mimi::transformer::RotaryEmbedding
• models::mimi::transformer::StreamingMultiheadAttention
• models::mimi::transformer::StreamingMultiheadCrossAttention
• models::mimi::transformer::StreamingTransformer
• models::mimi::transformer::StreamingTransformerLayer
• models::mistral::Config
• models::mistral::Model
• models::mixformer::Config
• models::mixformer::MixFormerSequentialForCausalLM
• models::mixtral::Config
• models::mixtral::Model
• models::mmdit::blocks::ContextQkvOnlyJointBlock
• models::mmdit::blocks::DiTBlock
• models::mmdit::blocks::FinalLayer
• models::mmdit::blocks::LayerNormNoAffine
• models::mmdit::blocks::MMDiTJointBlock
• models::mmdit::blocks::MMDiTXJointBlock
• models::mmdit::blocks::ModulateIntermediates
• models::mmdit::blocks::QkvOnlyDiTBlock
• models::mmdit::blocks::SelfAttnDiTBlock
• models::mmdit::blocks::SelfAttnModulateIntermediates
• models::mmdit::embedding::PatchEmbedder
• models::mmdit::embedding::PositionEmbedder
• models::mmdit::embedding::TimestepEmbedder
• models::mmdit::embedding::Unpatchifier
• models::mmdit::embedding::VectorEmbedder
• models::mmdit::model::Config
• models::mmdit::model::MMDiT
• models::mmdit::model::MMDiTCore
• models::mmdit::projections::AttnProjections
• models::mmdit::projections::Mlp
• models::mmdit::projections::Qkv
• models::mmdit::projections::QkvOnlyAttnProjections
• models::mobileclip::MobileClipConfig
• models::mobileclip::MobileClipModel
• models::mobilenetv4::Config
• models::mobileone::Config
• models::moondream::Config
• models::moondream::Encoder
• models::moondream::Model
• models::moondream::VisionConfig
• models::moondream::VisionEncoder
• models::mpt::Config
• models::mpt::Model
• models::nvembed_v2::embedding::Model
• models::nvembed_v2::model::Model
• models::olmo::Config
• models::olmo::Model
• models::openclip::text_model::Config
• models::openclip::text_model::Encoder
• models::openclip::text_model::OpenClipTextTransformer
• models::paligemma::Config
• models::paligemma::Model
• models::paligemma::MultiModalProjector
• models::parler_tts::Attention
• models::parler_tts::Config
• models::parler_tts::Decoder
• models::parler_tts::DecoderConfig
• models::parler_tts::DecoderLayer
• models::parler_tts::Model
• models::persimmon::Config
• models::phi3::Config
• models::phi3::Model
• models::phi3::RotaryEmbedding
• models::phi::Config
• models::phi::Model
• models::pixtral::llava::Config
• models::pixtral::llava::Model
• models::pixtral::llava::MultiModalProjector
• models::pixtral::vision_model::Config
• models::pixtral::vision_model::Model
• models::quantized_blip::BlipForConditionalGeneration
• models::quantized_blip::VisionModel
• models::quantized_blip_text::TextLMHeadModel
• models::quantized_blip_text::TextPooler
• models::quantized_llama2_c::QLlama
• models::quantized_llama::ModelWeights
• models::quantized_metavoice::transformer::Model
• models::quantized_mistral::Model
• models::quantized_mixformer::MixFormerSequentialForCausalLM
• models::quantized_moondream::Encoder
• models::quantized_moondream::Model
• models::quantized_moondream::VisionEncoder
• models::quantized_mpt::Model
• models::quantized_phi3::ModelWeights
• models::quantized_phi::ModelWeights
• models::quantized_qwen2::ModelWeights
• models::quantized_recurrent_gemma::Model
• models::quantized_rwkv_v5::Model
• models::quantized_rwkv_v6::Model
• models::quantized_stable_lm::Model
• models::quantized_t5::Config
• models::quantized_t5::T5EncoderModel
• models::quantized_t5::T5ForConditionalGeneration
• models::qwen2::Config
• models::qwen2::Model
• models::qwen2::ModelForCausalLM
• models::qwen2_moe::Config
• models::qwen2_moe::Model
• models::recurrent_gemma::Config
• models::recurrent_gemma::Model
• models::repvgg::Config
• models::rwkv_v5::Config
• models::rwkv_v5::Model
• models::rwkv_v5::State
• models::rwkv_v5::StatePerLayer
• models::rwkv_v5::Tokenizer
• models::rwkv_v6::Model
• models::segformer::Config
• models::segformer::ImageClassificationModel
• models::segformer::SemanticSegmentationModel
• models::segment_anything::LayerNorm2d
• models::segment_anything::MlpBlock
• models::segment_anything::image_encoder::ImageEncoderViT
• models::segment_anything::mask_decoder::MaskDecoder
• models::segment_anything::prompt_encoder::PromptEncoder
• models::segment_anything::sam::Sam
• models::segment_anything::tiny_vit::TinyViT
• models::segment_anything::transformer::TwoWayTransformer
• models::siglip::Config
• models::siglip::Model
• models::siglip::TextConfig
• models::siglip::TextModel
• models::siglip::TextTransformer
• models::siglip::VisionConfig
• models::siglip::VisionModel
• models::stable_diffusion::StableDiffusionConfig
• models::stable_diffusion::attention::AttentionBlock
• models::stable_diffusion::attention::AttentionBlockConfig
• models::stable_diffusion::attention::CrossAttention
• models::stable_diffusion::attention::SpatialTransformer
• models::stable_diffusion::attention::SpatialTransformerConfig
• models::stable_diffusion::clip::ClipTextTransformer
• models::stable_diffusion::clip::Config
• models::stable_diffusion::ddim::DDIMScheduler
• models::stable_diffusion::ddim::DDIMSchedulerConfig
• models::stable_diffusion::ddpm::DDPMScheduler
• models::stable_diffusion::ddpm::DDPMSchedulerConfig
• models::stable_diffusion::embeddings::TimestepEmbedding
• models::stable_diffusion::embeddings::Timesteps
• models::stable_diffusion::euler_ancestral_discrete::EulerAncestralDiscreteScheduler
• models::stable_diffusion::euler_ancestral_discrete::EulerAncestralDiscreteSchedulerConfig
• models::stable_diffusion::resnet::ResnetBlock2D
• models::stable_diffusion::resnet::ResnetBlock2DConfig
• models::stable_diffusion::unet_2d::BlockConfig
• models::stable_diffusion::unet_2d::UNet2DConditionModel
• models::stable_diffusion::unet_2d::UNet2DConditionModelConfig
• models::stable_diffusion::unet_2d_blocks::CrossAttnDownBlock2D
• models::stable_diffusion::unet_2d_blocks::CrossAttnDownBlock2DConfig
• models::stable_diffusion::unet_2d_blocks::CrossAttnUpBlock2D
• models::stable_diffusion::unet_2d_blocks::CrossAttnUpBlock2DConfig
• models::stable_diffusion::unet_2d_blocks::DownBlock2D
• models::stable_diffusion::unet_2d_blocks::DownBlock2DConfig
• models::stable_diffusion::unet_2d_blocks::DownEncoderBlock2D
• models::stable_diffusion::unet_2d_blocks::DownEncoderBlock2DConfig
• models::stable_diffusion::unet_2d_blocks::UNetMidBlock2D
• models::stable_diffusion::unet_2d_blocks::UNetMidBlock2DConfig
• models::stable_diffusion::unet_2d_blocks::UNetMidBlock2DCrossAttn
• models::stable_diffusion::unet_2d_blocks::UNetMidBlock2DCrossAttnConfig
• models::stable_diffusion::unet_2d_blocks::UpBlock2D
• models::stable_diffusion::unet_2d_blocks::UpBlock2DConfig
• models::stable_diffusion::unet_2d_blocks::UpDecoderBlock2D
• models::stable_diffusion::unet_2d_blocks::UpDecoderBlock2DConfig
• models::stable_diffusion::uni_pc::EdmDpmMultistepScheduler
• models::stable_diffusion::uni_pc::ExponentialSigmaSchedule
• models::stable_diffusion::uni_pc::KarrasSigmaSchedule
• models::stable_diffusion::uni_pc::UniPCSchedulerConfig
• models::stable_diffusion::vae::AutoEncoderKL
• models::stable_diffusion::vae::AutoEncoderKLConfig
• models::stable_diffusion::vae::DiagonalGaussianDistribution
• models::stable_lm::Config
• models::stable_lm::Model
• models::starcoder2::Config
• models::starcoder2::Model
• models::stella_en_v5::Config
• models::stella_en_v5::EmbedHead
• models::stella_en_v5::EmbeddingModel
• models::stella_en_v5::Embeddings
• models::stella_en_v5::Model
• models::t5::ActivationWithOptionalGating
• models::t5::Config
• models::t5::Linear
• models::t5::T5EncoderModel
• models::t5::T5ForConditionalGeneration
• models::trocr::TrOCRConfig
• models::trocr::TrOCRDecoder
• models::trocr::TrOCREncoder
• models::trocr::TrOCRForCausalLM
• models::trocr::TrOCRModel
• models::vgg::Vgg
• models::vit::Config
• models::vit::Embeddings
• models::vit::Encoder
• models::vit::Model
• models::whisper::Config
• models::whisper::model::AudioEncoder
• models::whisper::model::TextDecoder
• models::whisper::model::Whisper
• models::whisper::quantized_model::AudioEncoder
• models::whisper::quantized_model::TextDecoder
• models::whisper::quantized_model::Whisper
• models::with_tracing::Conv2d
• models::with_tracing::Embedding
• models::with_tracing::LayerNorm
• models::with_tracing::Linear
• models::with_tracing::QMatMul
• models::with_tracing::RmsNorm
• models::wuerstchen::attention_processor::Attention
• models::wuerstchen::common::AttnBlock
• models::wuerstchen::common::GlobalResponseNorm
• models::wuerstchen::common::LayerNormNoWeights
• models::wuerstchen::common::ResBlock
• models::wuerstchen::common::TimestepBlock
• models::wuerstchen::common::WLayerNorm
• models::wuerstchen::ddpm::DDPMWScheduler
• models::wuerstchen::ddpm::DDPMWSchedulerConfig
• models::wuerstchen::diffnext::ResBlockStageB
• models::wuerstchen::diffnext::WDiffNeXt
• models::wuerstchen::paella_vq::MixingResidualBlock
• models::wuerstchen::paella_vq::PaellaVQ
• models::wuerstchen::prior::WPrior
• models::xlm_roberta::Config
• models::xlm_roberta::XLMRobertaForMaskedLM
• models::xlm_roberta::XLMRobertaForSequenceClassification
• models::xlm_roberta::XLMRobertaModel
• models::yi::Config
• models::yi::Model
• object_detection::Bbox
• object_detection::KeyPoint
• quantized_nn::Embedding
• quantized_nn::Linear
• quantized_nn::RmsNorm
• quantized_var_builder::VarBuilder

Enums

• generation::Sampling
• models::bert::HiddenAct
• models::bert::PositionEmbeddingType
• models::chinese_clip::Activation
• models::chinese_clip::EncoderConfig
• models::chinese_clip::text_model::PositionEmbeddingType
• models::clip::EncoderConfig
• models::clip::text_model::Activation
• models::encodec::NormType
• models::encodec::PadMode
• models::granite::GraniteEosToks
• models::granite::GraniteRopeType
• models::jina_bert::PositionEmbeddingType
• models::llama::Llama3RopeType
• models::llama::LlamaEosToks
• models::metavoice::gpt::AttnKernelType
• models::metavoice::gpt::NonLinearityType
• models::metavoice::gpt::NormType
• models::mimi::NormType
• models::mimi::conv::Norm
• models::mimi::conv::PadMode
• models::mimi::encodec::ResampleMethod
• models::mimi::transformer::Mlp
• models::mimi::transformer::Norm
• models::mimi::transformer::PositionalEmbedding
• models::persimmon::PositionEmbeddingType
• models::recurrent_gemma::TemporalBlockType
• models::stable_diffusion::clip::Activation
• models::stable_diffusion::ddpm::DDPMVarianceType
• models::stable_diffusion::schedulers::BetaSchedule
• models::stable_diffusion::schedulers::PredictionType
• models::stable_diffusion::schedulers::TimestepSpacing
• models::stable_diffusion::uni_pc::AlgorithmType
• models::stable_diffusion::uni_pc::CorrectorConfiguration
• models::stable_diffusion::uni_pc::FinalSigmasType
• models::stable_diffusion::uni_pc::SigmaSchedule
• models::stable_diffusion::uni_pc::SolverType
• models::stable_diffusion::uni_pc::TimestepSchedule
• models::stella_en_v5::EmbedDim
• models::stella_en_v5::ModelVariant
• models::vgg::Models

Traits

• models::flux::WithForward
• models::mmdit::blocks::JointBlock
• models::stable_diffusion::schedulers::Scheduler
• models::stable_diffusion::schedulers::SchedulerConfig
• models::whisper::audio::Float

Functions

• models::beit::vit_base
• models::beit::vit_large
• models::chinese_clip::div_l2_norm
• models::clip::div_l2_norm
• models::convmixer::c1024_20
• models::convmixer::c1536_20
• models::convnext::convnext
• models::convnext::convnext_no_final_layer
• models::dinov2::vit_small
• models::dinov2reg4::vit_base
• models::dinov2reg4::vit_small
• models::efficientvit::efficientvit
• models::efficientvit::efficientvit_no_final_layer
• models::encodec::conv1d_weight_norm
• models::encodec::conv_transpose1d_weight_norm
• models::eva2::vit_base
• models::eva2::vit_large
• models::fastvit::fastvit
• models::fastvit::fastvit_no_final_layer
• models::flux::sampling::denoise
• models::flux::sampling::get_noise
• models::flux::sampling::get_schedule
• models::flux::sampling::unpack
• models::hiera::hiera
• models::hiera::hiera_no_final_layer
• models::llava::utils::get_anyres_image_grid_shape
• models::llava::utils::select_best_resolution
• models::mimi::encodec::load
• models::mobileclip::div_l2_norm
• models::mobilenetv4::mobilenetv4
• models::mobilenetv4::mobilenetv4_no_final_layer
• models::mobileone::mobileone
• models::mobileone::mobileone_no_final_layer
• models::repvgg::repvgg
• models::repvgg::repvgg_no_final_layer
• models::resnet::resnet101
• models::resnet::resnet101_no_final_layer
• models::resnet::resnet152
• models::resnet::resnet152_no_final_layer
• models::resnet::resnet18
• models::resnet::resnet18_no_final_layer
• models::resnet::resnet34
• models::resnet::resnet34_no_final_layer
• models::resnet::resnet50
• models::resnet::resnet50_no_final_layer
• models::segment_anything::linear
• models::segment_anything::tiny_vit::tiny_vit_5m
• models::stable_diffusion::build_clip_transformer
• models::stable_diffusion::utils::interp
• models::stable_diffusion::utils::linspace
• models::t5::deserialize_feed_forward_proj_activation
• models::t5::linear_no_bias
• models::whisper::audio::log_mel_spectrogram_
• models::whisper::audio::pcm_to_mel
• models::with_tracing::conv2d
• models::with_tracing::layer_norm
• models::with_tracing::linear
• models::with_tracing::linear_b
• models::with_tracing::linear_no_bias
• object_detection::iou
• object_detection::non_maximum_suppression
• object_detection::soft_non_maximum_suppression
• quantized_nn::layer_norm
• quantized_nn::layer_norm_no_bias
• quantized_nn::linear
• quantized_nn::linear_b
• quantized_nn::linear_no_bias
• utils::apply_repeat_penalty
• utils::repeat_kv

Type Aliases

• models::quantized_blip::Config
• models::quantized_blip::VisionConfig
• models::quantized_blip_text::Config

Constants

• models::bert::DTYPE
• models::distilbert::DTYPE
• models::granite::DEFAULT_MAX_SEQ_LEN
• models::jina_bert::DTYPE
• models::llama::DEFAULT_MAX_SEQ_LEN
• models::persimmon::DTYPE
• models::quantized_llama::MAX_SEQ_LEN
• models::quantized_phi::MAX_SEQ_LEN
• models::segment_anything::sam::IMAGE_SIZE
• models::whisper::CHUNK_LENGTH
• models::whisper::COMPRESSION_RATIO_THRESHOLD
• models::whisper::DTYPE
• models::whisper::EOT_TOKEN
• models::whisper::HOP_LENGTH
• models::whisper::LOGPROB_THRESHOLD
• models::whisper::NO_SPEECH_THRESHOLD
• models::whisper::NO_SPEECH_TOKENS
• models::whisper::NO_TIMESTAMPS_TOKEN
• models::whisper::N_FFT
• models::whisper::N_FRAMES
• models::whisper::N_SAMPLES
• models::whisper::SAMPLE_RATE
• models::whisper::SOT_TOKEN
• models::whisper::TEMPERATURES
• models::whisper::TRANSCRIBE_TOKEN
• models::whisper::TRANSLATE_TOKEN