List of all items
Structs
- AttentionConfig
- ModelConfig
- ModelInfo
- RopeScaling
- common::families::AudioBuffer
- common::families::EncoderState
- common::families::SpeakerRef
- common::families::TranscriptSegment
- common::llm::LlmRuntimeConfig
- common::paged_pool::BlockAllocator
- common::paged_pool::PagedSeqState
- 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
- models::qwen3_moe::Qwen3MoeLayerState
- models::qwen3_moe::Qwen3MoeModel
- models::qwen3_moe::Qwen3MoeScratch
- moe::dispatch::DeviceRouteScratch
- moe::dispatch::ExpertStack
- moe::dispatch::MoeBucketPlan
- moe::dispatch::MoeForwardBucketedParams
- moe::dispatch::MoeForwardParams
- moe::dispatch::MoeRouteScratch
- moe::layer::Qwen3MoeLayer
- moe::router::RouterOutput
- moe_config::Qwen3MoeConfig
- multimodal::bert::BertModelWrapper
- multimodal::clip::ClipModelWrapper
- multimodal::qwen3_tts::Qwen3TTSTalker
- multimodal::qwen3_tts::SubTalker
- multimodal::qwen3_tts::TalkerConfig
- multimodal::qwen3_tts_backbone::TalkerBackboneBackend
- multimodal::qwen3_tts_backend::Qwen3TtsSubTalker
- multimodal::qwen3_tts_backend::Qwen3TtsTalker
- multimodal::qwen3_tts_vocoder::Qwen3TTSVocoder
- multimodal::qwen3_tts_vocoder::VocoderConfig
- multimodal::speaker_encoder::SpeakerEncoder
- multimodal::speech_tokenizer_encoder::SpeechTokenizerEncoder
- multimodal::whisper::WhisperModelWrapper
- registry::DefaultModelRegistry
- registry::ModelAlias
- registry::ModelDiscoveryEntry
- source::DefaultModelSourceResolver
- source::ModelSourceConfig
- source::ResolvedModelSource
- tensor_wrapper::CandleTensorWrapper
- tokenizer::PlaceholderTokenizer
- tokenizer::TokenizerFactory
- tokenizer::TokenizerHandle
Enums
- Activation
- ModelType
- NormType
- gguf_runtime::GgufArch
- gguf_runtime::GgufRuntime
- models::llama_family::RopeScalingConfig
- registry::Architecture
- registry::ModelFormatType
- source::ModelFormat
- weight_format::WeightFormat
Traits
- ModelExecutor
- common::families::EmbeddingModel
- common::families::EncoderDecoderLM
- common::families::MultimodalLLM
- common::families::Transcriber
- common::families::TtsModel
- common::llm::DecoderOnlyLLM
- multimodal::qwen3_tts_backbone::TalkerBackboneForward
- source::ModelSourceResolver
Functions
- audio_processor::chunk_pcm
- audio_processor::load_audio
- audio_processor::load_audio_at_rate
- audio_processor::load_audio_bytes
- common::decoder_unified::compute_cu_seqlens_q
- common::decoder_unified::compute_final_indices
- common::decoder_unified::compute_max_kv_len
- common::decoder_unified::compute_pos_offsets
- common::decoder_unified::concat_q_tokens
- common::decoder_unified::stack_block_tables
- common::decoder_unified::unified_graph_key
- common::paged_pool::block_hash
- common::paged_pool::block_hash_chain
- executor::common::default_executor_status
- executor::common::tensor_to_tokens
- executor::common::tokens_to_tensor
- executor::common::wrap_tensor
- executor::tts_executor::sample_token
- gguf_engine_loader::auto_discover_tokenizer_path
- gguf_engine_loader::is_gguf_path
- gguf_engine_loader::load_gguf_decoder
- gguf_engine_loader::load_gguf_decoder_with_info
- loader::gptq_loader::load_gptq_weights
- mel::log_mel_spectrogram
- moe::dispatch::moe_forward
- moe::dispatch::moe_forward_bucketed
- moe::dispatch::moe_forward_cpu
- moe::router::route
- moe::router::route_into
- multimodal::speaker_encoder::mel_spectrogram_speaker_encoder
Type Aliases
- Result
- common::families::AudioTokens
- common::families::ImageBuffer
- common::families::PcmSamples
- common::families::VisualTokens
- common::paged_pool::BlockHash
Statics
- moe::dispatch::MOE_BUCKET_COMBINE_US
- moe::dispatch::MOE_BUCKET_D2H_US
- moe::dispatch::MOE_BUCKET_GATHER_US
- moe::dispatch::MOE_BUCKET_GEMM1_US
- moe::dispatch::MOE_BUCKET_GEMM3_US
- moe::dispatch::MOE_BUCKET_LAYER_CALLS
- moe::dispatch::MOE_BUCKET_PLAN_US
- moe::dispatch::MOE_BUCKET_ROUTE_US
- moe::dispatch::MOE_BUCKET_SILU_US
- moe::dispatch::MOE_BUCKET_SYNC_US
- moe::dispatch::MOE_COPY_CALLS
- moe::dispatch::MOE_COPY_US
- moe::dispatch::MOE_GEMV_DOWN_CALLS
- moe::dispatch::MOE_GEMV_DOWN_US
- moe::dispatch::MOE_GEMV_GATE_UP_CALLS
- moe::dispatch::MOE_GEMV_GATE_UP_US
- moe::dispatch::MOE_HOST_TOPK_CALLS
- moe::dispatch::MOE_HOST_TOPK_US
- moe::dispatch::MOE_SCALED_ADD_CALLS
- moe::dispatch::MOE_SCALED_ADD_US
- moe::dispatch::MOE_SILU_CALLS
- moe::dispatch::MOE_SILU_US
- moe::dispatch::MOE_SYNC_CALLS
- moe::dispatch::MOE_SYNC_US