🧠 LLM Inference - emschwartz · Scour

FairyFuse: Multiplication-Free LLM Inference on CPUs via Fused Ternary Kernels 🕯️Candle

Scalable Inference Architectures for Compound AI Systems: A Production Deployment Study 🏗️LLM Infrastructure

One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement 🏗️LLM Infrastructure

Distributed Generative Inference of LLM at Internet Scales with Multi-Dimensional Communication Optimization 🏗️LLM Infrastructure

Nautile-370M: Spectral Memory Meets Attention in a Small Reasoning Model 🪄Prompt Engineering

Calibeating Prediction-Powered Inference 🧠Inference Serving

DiP-SD: Distributed Pipelined Speculative Decoding for Efficient LLM Inference at the Edge 🏗️LLM Infrastructure

A Task Decomposition and Planning Framework for Efficient LLM Inference in AI-Enabled WiFi-Offload Networks 🏗️LLM Infrastructure

Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs 📦Batch Embeddings

Large Language Models Decide Early and Explain Later 🏗️LLM Infrastructure

HGQ-LUT: Fast LUT-Aware Training and Efficient Architectures for DNN Inference 🔢BitNet Inference

Language as a Latent Variable for Reasoning Optimization 🏆LLM Benchmarking

No more posts from emschwartz's subscribed feeds.

Scour all 24432 feeds Learn more about Feeds

Log in to enable infinite scrolling