neural-compressor icon indicating copy to clipboard operation
neural-compressor copied to clipboard

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

Results 155 neural-compressor issues
Sort by recently updated
recently updated
newest added

When I use "basic" strategy tuning to quantize my model, I ran into this issue during one of the phases: ``` ... 2024-02-21 23:25:49 [INFO] Tune 73 result is: [Accuracy...

## Type of Change Examples ## Description Examples for HQQ ## How has this PR been tested? Local test

examples

## Type of Change Add ipex xpu examples ## Description - [ ] ResNet50 - [ ] yolo - [ ] gptj - [ ] llama2 ## Expected Behavior &...

## Type of Change Example code ## Description Dreambooth is a method customize text-to-image models like Stable Diffusion with a few (3-5) images of a subject. This example illustrates how...

## Type of Change As per title. ## Description This PR includes two new features for SmoothQuant (that I was too lazy to split into two PRs): * Add the...

enhancement
pending

…mple ## Type of Change feature or bug fix or documentation or validation or others API changed or not ## Description detail description ## Expected Behavior & Potential Risk the...

won't merge

## Type of Change feature ## Description enable bias-shifting of outlier suppression + in SQ Note: this is still under development and debugging ## Expected Behavior & Potential Risk ##...

won't merge

## Type of Change Documentation for RFC submission ## Description This is a proposed RFC for DeepSpeed/INC integration

documentation
won't merge