furnace-server 0.10.0

Fast, unified, Rust-native, Axum-compatible inference endpoints for Burn models and LLMs: KServe / Triton and OpenAI APIs from one pure-Rust server
Documentation 
1
2
3
4
5
6
7
8
9
10

use serde::{Deserialize, Serialize};

/// Tensor specification for model metadata
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct TensorSpec {
    pub shape: Vec<usize>,
    pub dtype: String,
    pub min_value: Option<f32>,
    pub max_value: Option<f32>,
}