List of all items

Structs

• AttentionConfig
• ModelConfig
• ModelInfo
• RopeScaling
• architectures::bert::BertModelWrapper
• architectures::clip::ClipModelWrapper
• architectures::qwen3_tts::Qwen3TTSTalker
• architectures::qwen3_tts::SubTalker
• architectures::qwen3_tts::TalkerConfig
• architectures::qwen3_tts_backbone::TalkerBackboneBackend
• architectures::qwen3_tts_backend::Qwen3TtsSubTalker
• architectures::qwen3_tts_backend::Qwen3TtsTalker
• architectures::qwen3_tts_vocoder::Qwen3TTSVocoder
• architectures::qwen3_tts_vocoder::VocoderConfig
• architectures::speaker_encoder::SpeakerEncoder
• architectures::speech_tokenizer_encoder::SpeechTokenizerEncoder
• architectures::whisper::WhisperModelWrapper
• builder::DefaultModelBuilderFactory
• builder::SimpleModelBuilder
• common::families::AudioBuffer
• common::families::EncoderState
• common::families::SpeakerRef
• common::families::TranscriptSegment
• common::llm::LlmRuntimeConfig
• definition::ConfigManager
• definition::ModelDefinition
• executor::bert_executor::BertModelExecutor
• executor::clip_executor::ClipModelExecutor
• executor::common::GenericKvCacheHandle
• executor::llm_executor::LlmExecutor
• executor::stub_executor::StubModelExecutor
• executor::tts_executor::TtsModelExecutor
• executor::whisper_executor::WhisperModelExecutor
• hf_download::HfDownloader
• image_processor::ClipImageProcessor
• loader::gptq_loader::GptqLayerWeights
• loader::gptq_loader::QuantizeConfig
• loader::safetensors_loader::SafeTensorsLoader
• models::llama_family::LlamaFamilyConfig
• models::llama_family::LlamaFamilyLayer
• models::llama_family::LlamaFamilyModel
• models::llama_family::LlamaFamilyScratch
• models::llama_family::RopeCache
• registry::DefaultModelRegistry
• registry::ModelAlias
• registry::ModelDiscoveryEntry
• source::DefaultModelSourceResolver
• source::ModelSourceConfig
• source::ResolvedModelSource
• tensor_wrapper::CandleTensorWrapper
• tokenizer::PlaceholderTokenizer
• tokenizer::TokenizerFactory
• tokenizer::TokenizerHandle
• weights::GGUFLoader
• weights::SafeTensorsLoader
• weights::StubWeightLoader
• weights::WeightLoaderHandle

Enums

• Activation
• ModelType
• NormType
• registry::Architecture
• registry::ModelFormatType
• source::ModelFormat

Traits

• ModelBuilder
• ModelExecutor
• WeightLoader
• architectures::qwen3_tts_backbone::TalkerBackboneForward
• common::families::EmbeddingModel
• common::families::EncoderDecoderLM
• common::families::MultimodalLLM
• common::families::Transcriber
• common::families::TtsModel
• common::llm::DecoderOnlyLLM
• source::ModelSourceResolver

Functions

• architectures::speaker_encoder::mel_spectrogram_speaker_encoder
• audio_processor::chunk_pcm
• audio_processor::load_audio
• audio_processor::load_audio_at_rate
• audio_processor::load_audio_bytes
• executor::common::default_executor_status
• executor::common::tensor_to_tokens
• executor::common::tokens_to_tensor
• executor::common::wrap_tensor
• executor::tts_executor::sample_token
• loader::gptq_loader::load_gptq_weights
• mel::log_mel_spectrogram
• weights::default_weight_loader

Type Aliases

• Result
• common::families::AudioTokens
• common::families::ImageBuffer
• common::families::PcmSamples
• common::families::VisualTokens

Constants

• audio_processor::CHUNK_SAMPLES