v0.1.8
meituan-longcat/LongCat-Videov0.1.8Mar 23, 2026by chonknick
Upgrading?
AI Summary
Achieves a 3.3x speedup in reranking performance through architectural optimizations like single-pass reranking and multi-threading.
Key Highlights
- 3.3x faster reranking performance (1.01s to 0.31s)
- Single rerank pass across packages
- Pre-optimized `.ort` model format
- Multi-threaded inference using available cores
New Features
- Single rerank pass implementation
- ORT format support with automatic fallback
- Memory-mapped 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 |
Related Repositories
public-apis/public-apis★ 491,310
A collective list of free APIs
NousResearch/hermes-agent★ 256,156
The agent that grows with you
yt-dlp/yt-dlp★ 200,351
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,617
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,706
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.