List of all items
Structs
- AllowedTokens
- ConstrainedSampler
- DecodeState
- GenerationConfig
- GreedySampler
- JsonStructure
- KvCache
- QwenConfig
- QwenModel
- RotaryEmbedding
- SamplingConfig
- Shape
- SliceVocab
- StochasticSampler
- gpu_offload::GpuOutputHead
- traits::CpuBackend
- vision::preprocess::PreprocessConfig
- vision::preprocess::Rgb8
Enums
Traits
Functions
- generate
- generate_constrained
- generate_with_sampler
- gpu_offload::split_q8_0
- greedy_argmax
- load_matmul_weight
- load_matmul_weight_opt
- load_tensor_f32
- load_tensor_f32_opt
- mask_logits
- tensor_from_entry
- tokenizer_from_gguf
- vision::preprocess::gray_to_rgb8
- vision::preprocess::preprocess
- vision::preprocess::resize_square