Quantization skills

High-Performance LLM Serving

davila7

Optimize LLM API deployment with high throughput and low latency.

DINO Object Detection

nvidia

Train and deploy 2D object detection models with DINO.

RT-DETR

nvidia

Real-time object detection with competitive accuracy.

vLLM Serving

nousresearch

High-performance LLM serving for optimized inference.

GPTQ Quantization

davila7

Efficiently deploy large LLMs on consumer GPUs with minimal loss.

A

AWQ Quantization

davila7

Optimize large models with 4-bit quantization.

TensorRT-LLM

davila7

Optimize LLM inference for NVIDIA GPUs with TensorRT.

B

BitsAndBytes Quantization

davila7

Optimize LLMs with efficient quantization techniques.

GGUF Quantization

davila7

Efficient model deployment for consumer hardware.

H

Half-Quadratic Quantization

davila7

Efficient model quantization without calibration data.

Vector Search

ruvnet

Efficient vector search for large and small datasets.

TensorRT-LLM

nousresearch

Optimize LLM inference for NVIDIA GPUs.

A

AgentDB Performance Optimization

ruvnet

Enhance AgentDB efficiency with advanced techniques.