Files

mistralrs

anymoe.rs diffusion_model.rs gguf.rs gguf_lora_model.rs gguf_xlora_model.rs lib.rs lora_model.rs messages.rs model.rs speculative.rs text_model.rs vision_model.rs xlora_model.rs

mistralrs_bench

mistralrs_core

amoe

inputs.rs macros.rs mod.rs

cuda

diffusion_models

clip

flux

autoencoder.rs mod.rs model.rs sampling.rs stepper.rs

t5

mod.rs processor.rs

dummy_paged_attention

layers

mod.rs paged_attention.rs

block_engine.rs block_engine_sequence.rs cache_engine.rs config.rs mod.rs scheduler.rs

embedding

engine

add_request.rs logger.rs mod.rs

gguf

chat_template.rs content.rs gguf_tokenizer.rs mod.rs

lora

loralinear.rs mod.rs qloralinear.rs

models

deepseek2.rs deepseek3.rs gemma.rs gemma2.rs llama.rs mistral.rs mixtral.rs mod.rs phi2.rs phi3.rs phi3_5_moe.rs quantized_llama.rs quantized_phi2.rs quantized_phi3.rs quantized_qwen2.rs quantized_starcoder2.rs qwen2.rs starcoder2.rs

pipeline

loaders

diffusion_loaders.rs mod.rs normal_loaders.rs vision_loaders.rs

amoe.rs cache_manager.rs chat_template.rs diffusion.rs ggml.rs gguf.rs inputs_processor.rs isq.rs llg.rs macros.rs mod.rs normal.rs paths.rs processing.rs response.rs sampling.rs speculative.rs vision.rs

scheduler

default_scheduler.rs mod.rs

search

tools

mod.rs request.rs response.rs

topology

utils

debug.rs gguf_metadata.rs log.rs memory_usage.rs mod.rs model_config.rs normal.rs progress.rs tokenizer.rs tokens.rs unvarbuilder.rs varbuilder_utils.rs

vision_models

gemma3

config.rs inputs_processor.rs mmproj.rs mod.rs text.rs

idefics2

idefics2_input_processor.rs mod.rs

idefics3

config.rs inputs_processor.rs mod.rs vision.rs

llava

llava_llm

llama.rs mistral.rs mod.rs

config.rs llava15.rs llava_inputs_processor.rs llava_next.rs llava_next_inputs_processor.rs mod.rs utils.rs

minicpmo

config.rs inputs_processor.rs mod.rs resampler.rs

mistral3

config.rs inputs_processor.rs mod.rs vision.rs

mllama

config.rs inputs_processor.rs mod.rs text.rs vision.rs

phi3

mod.rs phi3_inputs_processor.rs

phi4

config.rs image_embedding.rs inputs_processor.rs mm_embedding.rs mod.rs

qwen2_5_vl

config.rs inputs_processor.rs mod.rs text.rs vision.rs

qwen2vl

config.rs inputs_processor.rs mod.rs text.rs vision.rs

clip.rs image_processor.rs mod.rs preprocessor_config.rs processor_config.rs siglip.rs

xlora_models

classifier.rs config.rs gemma.rs gemma2.rs llama.rs mistral.rs mixtral.rs mod.rs phi2.rs phi3.rs quantized_llama.rs quantized_phi3.rs starcoder2.rs

attention.rs device_map.rs distributed.rs layers.rs layers_masker.rs layers_utils.rs lib.rs model_loader.rs model_selected.rs ops.rs prefix_cacher.rs request.rs response.rs sampler.rs sequence.rs toml_selector.rs

mistralrs_paged_attn

mistralrs_quant

afq

bitsandbytes

blockwise_fp8

cublaslt

distributed

layers.rs mod.rs socket.rs

dummy

fp8

mod.rs quantize.rs

gguf

gptq

gptq_cpu.rs mod.rs

hqq

hqq_op.rs mod.rs optimize.rs quantize.rs

lora

mod.rs static_lora.rs

rotary

unquantized

utils

isq.rs mod.rs ops.rs uqff.rs

imatrix.rs lib.rs safetensors.rs

mistralrs_server

chat_completion.rs completions.rs image_generation.rs interactive_mode.rs main.rs openai.rs util.rs

mistralrs_vision

lib.rs ops.rs pad.rs transforms.rs utils.rs

mistralrs_core/dummy_paged_attention/layers/
mod.rs

Settings

Help

1pub mod paged_attention;
2
3pub use paged_attention::PagedAttention;