✨ Model optimizations in LLMs - pleto · Scour

Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression

📊AI Performance Profiling Academic

Train Models Faster with JAX and MaxText Using NVFP4 on NVIDIA Blackwell

🧠Large Language Models (LLMs) News Blog

developer.nvidia.com·

SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving

💬Prompt optimizations for LLM serving Academic

TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs

🔧Systems-level optimizations for LLM serving Academic

Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin

🔢Quantization of LLMs Academic

Value-and-Structure Alignment for Routing-Consistent Quantization of Mixture-of-Experts Models

🔢Quantization of LLMs Academic

Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry

🔢Quantization of LLMs Academic

On Low-Bit Quantization Errors in Speaker Verification: Diagnostic and Mitigation

🔢Quantization of LLMs Academic

NSVQ: Mitigating Codebook Collapse by Stabilizing Encoder Drift in Vector Quantization

🔢Quantization of LLMs Academic

OffQ: Taming Structured Outliers in LLM Quantization by Offsetting

🔢Quantization of LLMs Academic

ASH: Asymmetric Scalar Hashing With Learned Dimensionality Reduction for High-Fidelity Vector Quantization

🔍Retrieval-augmented generation Academic

Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs

🔢Quantization of LLMs Academic

Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents

🔢Quantization of LLMs Academic

Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models

🧠Large Language Models (LLMs) Academic

What Limits Does Quantization Place on Dense Top-$k$ Retrieval? A Theoretical Study

🔢Quantization of LLMs Academic

Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization

🔍Retrieval-augmented generation Academic

ViP-VL: Vietnamese Self-supervised Speech Pretraining Model with Vector-Quantization Learning

🧠Large Language Models (LLMs) Academic

FQA: A Full-Space Quantization-Driven Architecture for Hardware-Efficient Piecewise Approximation of Nonlinear Activation Functions

🔢Quantization of LLMs Academic

APEX4: Efficient Pure W4A4 LLM Inference via Intra-SM Compute Rebalancing

🔧Systems-level optimizations for LLM serving Academic

Beyond Per-Token Pricing: A Concurrency-Aware Methodology for LLM Infrastructure Cost Estimation

📊AI Performance Profiling Academic

Log in to enable infinite scrolling