neural-compressor
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
## Type of Change feature or bug fix or documentation or validation or others API changed or not ## Description detail description JIRA ticket: xxx ## Expected Behavior & Potential...
## Type of Change Add and update qat examples with new api Include: * resnet50 * resnet50v2 * resnet101 * resnet101v2 * dense169 * mobilenet_v2 ## Description JIRA: https://jira.devtools.intel.com/browse/ILITV-2209 ##...
## Type of Change bug fix API not changed ## Description detail description JIRA ticket: ILITV-2566 ## Expected Behavior & Potential Risk inception_v3,bert_large_squad_model_zoo,faster_rcnn_inception_resnet_v2,faster_rcnn_inception_resnet_v2_saved,faster_rcnn_resnet101,faster_rcnn_resnet101_saved can't reach the accuracy goal on SPR...
Signed-off-by: Xinyu Ye ## Type of Change API helper ## Description detail description JIRA ticket: xxx ## Expected Behavior & Potential Risk the expected behavior that triggered by this PR...
## Type of Change documentation ## Description Documentation refinement list: 1. validated_model_list.md 2. benchmark.md ## How has this PR been tested? Spell check and manual review. ## Dependency Change? No
## Type of Change bug fix API not changed ## Description detail description JIRA ticket: ILITV-1851 ## Expected Behavior & Potential Risk VAE-CF model can tune and run benchmark successfully....
## Type of Change docs refine - CODE_OF_CONDUCT.md - CONTRIBUTING.md ## Description - Rename `contributions.md` --> `CONTRIBUTING.md`, follow the [github docs contribution guidelines](https://docs.github.com/en/enterprise-cloud@latest/communities/setting-up-your-project-for-healthy-contributions/setting-guidelines-for-repository-contributors#adding-a-contributing-file) - Add content list - Update email...
## Type of Change doc string rst files for py scripts ## Description - config.py - mix_precision.py - adaptor/torch_utils ## Expected Behavior & Potential Risk the expected behavior that triggered...