🕯️ Candle ML - emschwartz · Scour

NestPipe: Large-Scale Recommendation Training on 1,500+ Accelerators via Nested Pipelining 📦Batch Embeddings

arxiv.org·6d

Claude Code doesn't trust Claude with permissions 🔌Claude Plugins

blog.raed.dev·4d·Hacker News

GPU Acceleration of Sparse Fully Homomorphic Encrypted DNNs ⚡Hardware Acceleration

arxiv.org·1d

Aethon: A Reference-Based Replication Primitive for Constant-Time Instantiation of Stateful AI Agents 💻Coding Agents

arxiv.org·5h·Hacker News

High-dimensional inference for the $\gamma$-ray sky with differentiable programming 🏗️LLM Infrastructure

arxiv.org·2d

CARO: Chain-of-Analogy Reasoning Optimization for Robust Content Moderation 🛡️Content Moderation

arxiv.org·1d

Why Smaller Is Slower? Dimensional Misalignment in Compressed LLMs 🎯Vector Quantization

arxiv.org·1d

SMT with Uninterpreted Functions and Monotonicity Constraints in Systems Biology 🧮SMT Solvers

arxiv.org·5d

InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models 🏗️LLM Infrastructure

arxiv.org·6d

Joint Optimization of Reasoning and Dual-Memory for Self-Learning Diagnostic Agent 🧠LLM Inference

arxiv.org·6d

VertAX: a differentiable vertex model for learning epithelial tissue mechanics 📦Batch Embeddings

arxiv.org·6d

No more posts from emschwartz's subscribed feeds.

Scour all 23985 feeds Learn more about Feeds