List of all items
Structs
- ArchSpec
- CacheConfig
- ContiguousKVCache
- LlamaModel
- ModelRegistry
- PageStats
- PagedKVCache
- Q40Weight
- Q4KWeight
- Q50Weight
- Q5KWeight
- Q6KWeight
- Q80Weight
- QuantizedLinear
- RotaryEmbedding
- SmolVlmModel
- WhisperModel
Enums
Traits
Functions
- dequantize_q4_0_gpu
- dequantize_q4_k_gpu
- dequantize_q5_0_gpu
- dequantize_q5_k_gpu
- dequantize_q6_k_gpu
- dequantize_q8_0_gpu
- image_prompt_expansion
- load_speech_model
- pixels_to_tensor
- repack_q4_0
- repack_q4_k
- repack_q5_0
- repack_q6_k
- repack_q8_0
- rms_norm
- try_quant_linear