🏗️ LLM Infrastructure - emschwartz · Scour

Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control 🧠LLM Inference

Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving 🧠LLM Inference

Incompressible Knowledge Probes: Estimating Black-Box LLM Parameter Counts via Factual Capacity 🧠LLM Inference

arxiv.org·2d·Hacker News

The Surprising Universality of LLM Outputs: A Real-Time Verification Primitive 🦙Ollama

Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis 🦙Ollama

PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference 🧠LLM Inference

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference 🧠LLM Inference

Hybrid JIT-CUDA Graph Optimization for Low-Latency Large Language Model Inference 📦Batch Embeddings

Exploring the Efficiency of 3D-Stacked AI Chip Architecture for LLM Inference with Voxel ⚡Hardware Acceleration

Parameter Efficiency Is Not Memory Efficiency: Rethinking Fine-Tuning for On-Device LLM Adaptation 🧠LLM Inference

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

Uncertainty Quantification for LLM Function-Calling 🧠LLM Inference

No more posts from emschwartz's subscribed feeds.

Scour all 24420 feeds Learn more about Feeds

Log in to enable infinite scrolling