127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “inference”

20,509 results

Local Ai

b9934

DGX agent

llama.cpp is an open-source software library that performs inference on various large language models , and b9934 represents a specific build release in the project's continuous versioning system. The

local-aillama-cpp-releases

9 Jul 2026

Local Ai

b9945

DGX agent

b9945 is a build-tagged release of llama.cpp, an open-source library that performs inference on large language models and is co-developed alongside the GGML tensor library. The llama.cpp project does

local-aillama-cpp-releases

Search: “inference”

b9934

b9945

Distributed Sparse Interventions in Language Models

Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories

LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting

PeTeR: Post-Training Robustification of Probabilistic Circuits

Physical activities enable scalable foundation modelling for broad-spectrum health prediction

Progressive Crystallization: Turning Agent Exploration into Deterministic, Lower-Cost Workflows in Production

STST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Prediction Architecture For EEG Self-Supervised Learning

The Key to Going Linear: Analysis-Driven Transformer Linearization

b9909

b9913

b9916

b9923

b9925

b9929

b9931

Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair

C4N, now GA: Delivering cloud’s highest per vCPU network and block storage I/O for x86 workloads

CCBENCH: Assessing LLM Cultural Competence via Implicitly Signaled Norms using Health Queries

DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression

From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b

KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta

Multi-Teacher Contrastive Distillation for Edge-Efficient Pathology Foundation Models

Open, convenient and predictable: Introducing Provisioned Throughput

Read our blog: https://www.together.ai/blog/provisioned-throughput

This is a big update that I’m excited to finally share. We launched our first dev platform for AI media in 2020, offering a simple API and a…

A Decomposable Probe for Few-Step Diffusion Models: Prompt, Latent, and Score Selectivity across Backbone Families and Distillation Paradigms

A Transformer-Based Contrastive Learning Approach for Few-Shot Sign Language Recognition

AI-RAN on NPUs: Baseband Processing Without Baseband Chips

APeB: Benchmarking Personalization Ability of Large Language Model Agents

ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs

b9895

Best-of-Better-N: Generating Pre-Aligned Responses with In-Context Learning

CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning

Constrained Flow Matching via Lagrangian Dual Flows

Context-Constrained Transfer Learning for Tabular Foundation Models via Data Distillation

Distribution Matching Distillation Meets Reinforcement Learning

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

Facing US export controls, China's DeepSeek plans to make its own chips

Folding, Reasoning, and Scaling with Open-source Drug Discovery Engine

Hierarchical Multi-to-Single-Modal Knowledge Distillation for Disruption Prediction in EAST

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

Integrating Neural Encoders in Bayesian Generalized Linear Mixed Models for Multimodal Data

Learning 3D Affordances for Blade Insertion in Cluttered Stowing

LLMoxie: Exploring Agentic AI for Scientific Software Development

MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration

PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction