Crate ferrum_testkit 

Mock components for testing the ferrum inference engine without GPU.

Provides MockTensor, MockModelExecutor, MockKvCacheManager, MockTokenizer, and MockSampler — all hardware-independent, suitable for testing the scheduling and orchestration layers on any platform.

Re-exports

pub use paged_executor::PagedAttentionExecutor;

pub use paged_executor::PagedExecutorConfig;

Modules

paged_executor

Model executor that uses PagedAttention KV cache.

Structs

MockKvCacheHandle

Mock KV cache handle — tracks block metadata without allocating real memory.

MockKvCacheManager

Mock KV cache manager — tracks allocations in memory, simulates block limits.

MockModelExecutor

Mock model executor that simulates prefill/decode with configurable latency. No model weights, no GPU — pure async simulation.

MockSampler

Greedy sampler — always picks the token with highest logit. Deterministic, no temperature or top-k.

MockTensor

A mock tensor that stores shape and optional f32 data. No GPU, no Candle — pure Rust.

MockTensorFactory

Mock tensor factory implementing TensorFactory without any ML backend.

MockTokenizer

Mock tokenizer: splits on whitespace, assigns sequential token IDs. EOS token is vocab_size - 1.