LLM

Optimizing LLM Inference Costs: A Comprehensive Guide
LLM

Optimizing LLM Inference Costs: A Comprehensive Guide

Explore strategies for benchmarking large language model (LLM) inference costs, enabling smarter scaling and deployment in the AI landscape, as detailed by NVIDIA's latest insights.

NVIDIA Introduces High-Performance FlashInfer for Efficient LLM Inference
LLM

NVIDIA Introduces High-Performance FlashInfer for Efficient LLM Inference

NVIDIA's FlashInfer enhances LLM inference speed and developer velocity with optimized compute kernels, offering a customizable library for efficient LLM serving engines.

Together AI Launches Cost-Efficient Batch API for LLM Requests
LLM

Together AI Launches Cost-Efficient Batch API for LLM Requests

Together AI introduces a Batch API that reduces costs by 50% for processing large language model requests. The service offers scalable, asynchronous processing for non-urgent workloads.

NVIDIA Introduces EoRA for Enhancing LLM Compression Without Fine-Tuning
LLM

NVIDIA Introduces EoRA for Enhancing LLM Compression Without Fine-Tuning

NVIDIA unveils EoRA, a fine-tuning-free solution for improving compressed large language models' (LLMs) accuracy, surpassing traditional methods like SVD.

NVIDIA Enhances Long-Context LLM Training with NeMo Framework Innovations
LLM

NVIDIA Enhances Long-Context LLM Training with NeMo Framework Innovations

NVIDIA's NeMo Framework introduces efficient techniques for long-context LLM training, addressing memory challenges and optimizing performance for models processing millions of tokens.

NVIDIA Unveils Advanced Optimization Techniques for LLM Training on Grace Hopper
LLM

NVIDIA Unveils Advanced Optimization Techniques for LLM Training on Grace Hopper

NVIDIA introduces advanced strategies for optimizing large language model (LLM) training on the Grace Hopper Superchip, enhancing GPU memory management and computational efficiency.

NVIDIA Grace Hopper Revolutionizes LLM Training with Advanced Profiling
LLM

NVIDIA Grace Hopper Revolutionizes LLM Training with Advanced Profiling

Explore how NVIDIA's Grace Hopper architecture and Nsight Systems optimize large language model (LLM) training, addressing computational challenges and maximizing efficiency.

Exploring LLM Agents and Their Role in AI Reasoning and Test Time Scaling
LLM

Exploring LLM Agents and Their Role in AI Reasoning and Test Time Scaling

Discover the impact of large language model (LLM) agents on AI reasoning and test time scaling, highlighting their use in workflows and chatbots, according to NVIDIA.

Together Introduces Code Interpreter API for Seamless LLM Code Execution
LLM

Together Introduces Code Interpreter API for Seamless LLM Code Execution

Together.ai launches the Together Code Interpreter (TCI), an API enabling developers to execute LLM-generated code securely and efficiently, enhancing agentic workflows and reinforcement learning operations.

NVIDIA Unveils Nemotron-CC: A Trillion-Token Dataset for Enhanced LLM Training
LLM

NVIDIA Unveils Nemotron-CC: A Trillion-Token Dataset for Enhanced LLM Training

NVIDIA introduces Nemotron-CC, a trillion-token dataset for large language models, integrated with NeMo Curator. This innovative pipeline optimizes data quality and quantity for superior AI model training.

Trending topics