Skip to main content

Module async_ops

Module async_ops 

Source
Expand description

NAPI-RS bindings for async and batch operations

Provides Node.js bindings for:

  • Async attention computation with tokio
  • Batch processing utilities
  • Parallel attention computation

Structs§

BatchConfig
Batch processing configuration
BatchResult
Batch processing result
BenchmarkResult
Benchmark result
ParallelConfig
Configuration for parallel attention
StreamProcessor
Stream processor for handling attention in chunks

Enums§

AttentionType
Attention type for parallel computation

Functions§

batch_attention_compute
Process a batch of attention computations
batch_flash_attention_compute
Process a batch with flash attention
benchmark_attention
Run attention benchmark
compute_attention_async
Async scaled dot-product attention computation
compute_flash_attention_async
Async flash attention computation
compute_hyperbolic_attention_async
Async hyperbolic attention computation
parallel_attention_compute
Parallel attention computation across multiple queries