GIGAZINE

AMD unveils proprietary inference model 'Instella-Math'

AMD has announced ' Instella-Math,' a language model trained exclusively on AMD GPUs. It has 3 billion parameters and is specialized for inference and mathematical problem solving. Instella-Math was ...
IEEE

SiRnn: A Math Library for Secure RNN Inference

Abstract: Complex machine learning (ML) inference algorithms like recurrent neural networks (RNNs) use standard functions from math libraries like exponentiation, sigmoid, tanh, and reciprocal of ...
The Next Platform

Doing The Math On CPU-Native AI Inference

A number of chip companies — importantly Intel and IBM, but also the Arm collective and AMD — have come out recently with new CPU designs that feature native Artificial Intelligence (AI) and its ...
Microsoft

SIRNN: A Math Library for Secure RNN Inference

Complex machine learning (ML) inference algorithms like recurrent neural networks (RNNs) use standard functions from math libraries like exponentiation, sigmoid, tanh, and reciprocal of square root.
Microsoft

LLAMA: A Low Latency Math Library for Secure Inference

Secure machine learning (ML) inference can provide meaningful privacy guarantees to both the client (holding sensitive input) and the server (holding sensitive weights of the ML model) while realizing ...
The Korea Times

LG CNS codevelops own inference-optimized large language model with Cohere

LG CNS, in collaboration with artificial intelligence (AI) startup Cohere, has developed an inference-optimized large language model (LLM) boasting over 111 billion parameters. The new LLM model comes ...
GitHub

Examining False Positives under Inference Scaling for Mathematical Reasoning

├── README.md ├── benchmarks │ ├── AIME.jsonl │ ├── MATH100.jsonl │ └── OmniMATH100-rule.jsonl ├── evaluation │ ├── eval-Qwen2.5_Math │ │ ├── get_results.py │ │ ├── grader.py │ │ ├── math_utils.py │ │ ...