v0.1.8
asheshgoplani/agent-deckv0.1.8Mar 23, 2026by chonknick
AI Summary
Overhauled reranking performance with optimizations including single-pass processing, ORT format support, and multi-threading.
Key Highlights
- Single rerank pass eliminating redundant ONNX session loads
- ORT format for faster model deserialization
- Mmap model loading for zero-copy memory access
- Multi-threaded inference (up to 4 cores)
New Features
- ORT format support
- Mmap model loading
- Multi-threaded inference
Full Release Notes
## What's Changed ### Reranking Performance Overhaul (3.3x faster) - **Single rerank pass** — collect all FTS5 results across packages, rerank once instead of per-package (eliminates redundant ONNX session loads) - **ORT format** — pre-optimized flatbuffer model (`reranker.ort`) for faster deserialization, with automatic fallback to `.onnx` - **mmap model loading** — zero-copy memory-mapped file access via `commit_from_memory_directly` - **Multi-threaded inference** — uses half available cores (capped at 4) for ONNX intra-op parallelism ### Benchmarks | Scenario | v0.1.7 | v0.1.8 | Speedup | |----------|--------|--------|---------| | All packages (11) | 1.01s | **0.31s** | 3.3x | | Single package | 0.09s | **0.04s** | 2.3x |