npx claudepluginhub plurigrid/asi --plugin asiThis skill uses the workspace's default tool permissions.
> *"The K-Scale model export and inference tool"*
Indexes K-Scale Labs robotics skills for humanoid robot development, RL training, sim-to-real transfer, and deployment. Organizes 9 skills in GF(3) triadic structure.
Guides efficient ML/AI app development in Rust, covering tensor handling with ndarray, GPU inference via candle/tch-rs/burn, ONNX portability with tract, data pipelines with polars, and batching/streaming patterns.
Guides training RL agents with Stable Baselines3 (PPO, SAC, DQN, TD3, DDPG, A2C), custom Gym environments, callbacks for monitoring, vectorized envs for parallel training, and deep RL workflows.
Share bugs, ideas, or general feedback.
"The K-Scale model export and inference tool"
kinfer is K-Scale's model inference engine for deploying trained policies:
ort (ONNX Runtime)┌─────────────────────────────────────────────────────────────────────────┐
│ kinfer Inference Pipeline │
│ │
│ ┌──────────────┐ load ┌──────────────┐ │
│ │ ONNX Model │───────────────▶│ Runtime │ │
│ │ (.onnx) │ │ (ort-sys) │ │
│ └──────────────┘ └──────┬───────┘ │
│ │ │
│ ┌──────────────┐ step ┌──────┴───────┐ output │
│ │ Observation │───────────────▶│ Inference │───────────────▶Action │
│ │ (sensors) │ │ Engine │ │
│ └──────────────┘ └──────────────┘ │
│ │ │
│ ▼ │
│ ┌──────────────┐ │
│ │ Logger │ │
│ │ (NDJSON) │ │
│ └──────────────┘ │
└─────────────────────────────────────────────────────────────────────────┘
// Efficient async execution with GIL management
lazy_static! {
static ref RUNTIME: Runtime = Runtime::new().unwrap();
}
// Minimize latency by preparing inputs ahead of time
fn step_and_take_action(&mut self, observation: &[f32]) -> Vec<f32> {
// Pre-fetch next input while processing current
...
}
// Async logging thread for telemetry
struct Logger {
file: File,
tx: Sender<LogEntry>,
}
ort, ort-sys)Trit: -1 (MINUS)
Role: Verification/Validation (inference must be correct)
Color: #6E5FE4
URI: skill://kscale-kinfer#6E5FE4
kscale-kinfer (-1) ⊗ kscale-ksim (0) ⊗ onnx-export (+1) = 0 ✓
kscale-kinfer (-1) ⊗ rust-ml (0) ⊗ policy-training (+1) = 0 ✓
| Contributor | Focus Areas |
|---|---|
| b-vm | Step function, command names |
| codekansas | Performance, refactoring |
| WT-MM | Logging, env variables |
| alik-git | NDJSON logging, plotting |
| nfreq | Tokio runtime, GIL management |
import kinfer
# Load model
model = kinfer.load_model("walking_policy.onnx")
# Get observation from sensors
obs = get_sensor_data()
# Run inference
action = model.step(obs)
# Apply to actuators
apply_action(action)
use kinfer::InferenceEngine;
let mut engine = InferenceEngine::load("policy.onnx")?;
loop {
let obs = get_observation();
let action = engine.step_and_take_action(&obs);
send_to_actuators(&action);
}