← all releases
Sakana AI·Feb 11, 2026·v1.0·open source
SoftMatcha 2
SoftMatcha 2 is an ultra-fast and flexible search algorithm designed to perform searches over trillion-scale natural language corpora in under 0.3 seconds. It effectively handles semantic variations such as substitution, insertion, and deletion, making it a powerful tool for large-scale text analysis.
ML
overview
SoftMatcha 2 is an ultra-fast and flexible search algorithm designed to perform searches over trillion-scale natural language corpora in under 0.3 seconds. It effectively handles semantic variations such as substitution, insertion, and deletion, making it a powerful tool for large-scale text analysis.
key features
- 01Ultra-fast search over trillion-scale corpora
- 02Handles semantic variations (substitution, insertion, deletion)
- 03Employs suffix array-based string matching
- 04Disk-aware design for fast exact lookup
- 05Dynamic corpus-aware pruning to manage search space growth
related productsbrowse all →
SkyRL txopen sourceSkyRL tx is an open-source library that implements a backend for the Tinker API, enabling users to set up their own Tinker-like services on personal hardware. It supports end-to-end reinforcement learning (RL) and offers significantly faster sampling. The library is designed to be modular, allowing easy prototyping of new training algorithms, environments, and execution plans without compromising usability or speed.Step-Audio-R1open sourceStep-Audio-R1 is an advanced audio language model developed by StepFun AI, designed to enhance audio reasoning capabilities by grounding its reasoning in acoustic features. It introduces Modality-Grounded Reasoning Distillation (MGRD), an iterative training framework that shifts the model's reasoning from textual abstractions to acoustic properties, effectively addressing the 'inverted scaling' problem where performance degrades with longer reasoning. This model has demonstrated superior performance across various audio understanding and reasoning benchmarks, surpassing models like Gemini 2.5 Pro and achieving results comparable to Gemini 3 Pro.SINQopen sourceSINQ (Sinkhorn-Normalized Quantization) is a novel, fast, and high-quality quantization method designed to make any Large Language Model (LLM) smaller while preserving accuracy. It offers a plug-and-play, model-agnostic technique that delivers state-of-the-art performance for LLMs without sacrificing accuracy.