AI Wiki — Knowledge Base

CrofAI 'cheapest inference provider in the world' gets exposed as an OpenRouter wrapper, routing requests to smaller, cheaper models at up to 20x markup. CrofAI responds to Wire Fraud allegations by denying everything, then backtracking, then 3 hours later wiping their entire online presence

Disclaimer: no AI was used whatsoever to write this post Cautionary tale about chasing cheap tokens. exposé: https://kendell.dev/blog/crofaifalse/ reaction by nahcrof, announcing the shutdown of the s

model-releasesr-localllama

15 Sept 2026

Search: “inference”

The Inference Engineering Pareto Atlas: Which Optimizations Dominate the Cost, Quality, and Latency Frontier?

FlexEE: Self-Speculative and KV-Compatible Early Exiting for Offloading-Aware LLM Inference

CrofAI 'cheapest inference provider in the world' gets exposed as an OpenRouter wrapper, routing requests to smaller, cheaper models at up to 20x markup. CrofAI responds to Wire Fraud allegations by denying everything, then backtracking, then 3 hours later wiping their entire online presence

One Size Does Not Fit All: Setting Inference Depth from the Questions a Deployment Actually Asks

Self-Orchestrating Language Models: Leveraging Semantic Dependence for Efficient Inference

GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs

Vera Rubin NVL72 Agentic Inference: 67x better Performance per Dollar

Are inference providers able to make any margins?

Inference-Time Nash Alignment

Optimal Value Inference for Reinforcement Learning

Reduce inference cold starts on Amazon SageMaker HyperPod with model caching

Qualcomm signs a deal with Amazon to provide 'multiple generations of customized silicon' to help build AWS' AI infrastructure for inference; QCOM jumps ~5% (Ari Levy/CNBC)

Confounding-Valid Conformal Inference for Counterfactual KPIs in Wireless Networks

Self-Supervised Lexical Representation Learning for Fast, Large-Scale Phylogenetic Inference

A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference

GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories

Accessing OpenAI models on Amazon Bedrock from Australia with global cross-Region inference

Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States

Co-Designing AI Models Using Speculative Decoding for Faster LLM Inference

DynaNDE: Dynamic Near-Data Expert Scheduling for Batched MoE Inference

PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition

Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling

VoxGen, an AMD-optimized TTS inference engine for VoxCPM 2 models

CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration

Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference

Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers

Privacy Without Regret: Differentially Private Inference-Time Alignment

Spreading the load: How Salesforce met Multi-AZ HA with SageMaker Inference Components

Serving Kimi K3 at scale: An inference deep dive with Together AI https://x.com/i/broadcasts/1vKpPNBEjgMKE

CST: Collaborative Selective Transmission for Communication-Efficient Multimodal Edge Inference

Spatio-Temporal Parallelism for Diffusion Model Inference on Heterogeneous Multi-GPU Systems

Token-Level Likelihood-Array Regression for Membership Inference and AI-Generated Text Detection

TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics

Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo

Inference and Uncertainty Quantification for Streaming r-PCA

Pretraining Reusable Inference Across Views with Synthetic Task Priors

Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models

Counterpoint: “If alignment issues are becoming big enough that OpenAI is willing to commit 20% of research inference compute to chain-of-th…

AI inference chip startup Etched raised 700M led by its new server rack customer Jane Street at a 21B valuation, up from 10.3B after raising 300M in July (Robbie Whelan/Wall Street Journal)

From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems

Towards a theory of inference-time alignment with unknown rewards

Qwen3.8-Max is live on DigitalOcean Serverless Inference. Launching side by side with DigitalOcean as our Day 0 launch partner. Big model. S…

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference

User-Assisted Collaborative Distributed Inference for Efficient QoS-Aware Autoscaling

CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening

Demystifying Prediction Powered Inference

Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching

On the Effect of Sampling Diversity in Scaling LLM Inference