Performance skills

H

Half-Quadratic Quantization

davila7

Efficient model quantization without calibration data.

GPTQ Quantization

davila7

Efficiently deploy large LLMs on consumer GPUs with minimal loss.

GGUF Quantization

davila7

Efficient model deployment for consumer hardware.

Flash Attention Optimization

davila7

Enhance transformer performance with optimized attention.

B

BitsAndBytes Quantization

davila7

Optimize LLMs with efficient quantization techniques.

A

AWQ Quantization

davila7

Optimize large models with 4-bit quantization.

TensorBoard

davila7

Visualize and debug machine learning models effectively.

TensorRT-LLM

davila7

Optimize LLM inference for NVIDIA GPUs with TensorRT.

Llama.cpp

davila7

Efficient LLM inference on non-NVIDIA hardware.

Speculative Decoding

davila7

Accelerate LLM inference with advanced techniques.

M

Model Pruning

davila7

Compress LLMs and speed up inference with pruning techniques.

Performance Profiling

davila7

Measure, analyze, and optimize your web performance.