Thread-Safe Inference Cache | Dataford Interview Questions

Implement a thread-safe caching mechanism for model inference results.

Implement run_cached_inference(requests, capacity), where each request is a map containing a key and the result produced by inference. Return results in request order. The cache must use least-recently-used eviction, return the cached result for repeated keys, and remain safe when its cache operations are called concurrently. The supplied result is used only when the key is absent.

Constraints: 0 <= requests.length <= 100, 1 <= capacity <= 100, and keys are strings.

Constraints

0 <= requests.length <= 100
1 <= capacity <= 100
Each request contains a string key and an inference result
Keys are compared for exact equality

Function Signature

def run_cached_inference(requests, capacity):

Your question is Thread-Safe Inference Cache. Start with the requirements in the Question tab.

Run and submit as often as you like. When you're ready, talk me through your approach or go straight to the code.

Problem

Implement a thread-safe caching mechanism for model inference results.

Constraints: 0 <= requests.length <= 100, 1 <= capacity <= 100, and keys are strings.

Constraints

0 <= requests.length <= 100
1 <= capacity <= 100
Each request contains a string key and an inference result
Keys are compared for exact equality

Function Signature

def run_cached_inference(requests, capacity):

Your question is Thread-Safe Inference Cache. Start with the requirements in the Question tab.

Run and submit as often as you like. When you're ready, talk me through your approach or go straight to the code.