mistralrs-core 0.8.1

Fast, flexible LLM inference.
Documentation
pub(crate) mod deepseek2;
pub(crate) mod deepseek3;
pub(crate) mod gdn;
pub(crate) mod gemma;
pub(crate) mod gemma2;
pub(crate) mod glm4;
pub(crate) mod glm4_moe;
pub(crate) mod glm4_moe_lite;
pub(crate) mod gpt_oss;
pub(crate) mod granite;
pub(crate) mod llama;
pub(crate) mod mistral;
pub(crate) mod mixtral;
pub(crate) mod phi2;
pub(crate) mod phi3;
pub(crate) mod phi3_5_moe;
pub(crate) mod quantized_llama;
pub(crate) mod quantized_phi2;
pub(crate) mod quantized_phi3;
pub(crate) mod quantized_qwen;
pub(crate) mod quantized_qwen3;
pub(crate) mod quantized_qwen3_moe;
pub(crate) mod quantized_starcoder2;
pub(crate) mod qwen2;
pub(crate) mod qwen3;
pub(crate) mod qwen3_moe;
pub(crate) mod qwen3_next;
pub(crate) mod smollm3;
pub(crate) mod starcoder2;