neural-compressor
neural-compressor copied to clipboard
intel
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
Signed-off-by: Zhang, Weiwei1 ## Type of Change feature or bug fix or documentation or validation or others API changed or not ## Description detail description JIRA ticket: xxx ## Expected...
Signed-off-by: XuhuiRen ## Docstring Docstring for newAPI, contrib, and algorithm. ## Description Add docstring for the document and add some function description. detail description JIRA ticket: https://jira.devtools.intel.com/secure/RapidBoard.jspa?rapidView=32982&projectKey=ILITV&view=detail&selectedIssue=ILITV-2573&quickFilter=130297
## Type of Change - Documentation - API changed or not: None ## Description detail description JIRA ticket: [ILITV-2564](https://jira.devtools.intel.com/browse/ILITV-2564) ## Expected Behavior & Potential Risk None ## How has this...
Signed-off-by: spycsh ## 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...
## Type of Change docs refine - distributed.md ## Description 1. Title: Capitalize the first letter & Modify title name 2. Add content list 3. Fix the relative path link...
Signed-off-by: mengniwa ## Type of Change example update ## How has this PR been tested? extension test
Signed-off-by: yuwenzho ## Type of Change docstring ## Description model /base_model.py model /model.py model /nets_factory.py model /onnx_model.py model /torch_model.py model /__init__.py ## Dependency Change? no
## Type of Change documentation ## Description Documentation refinement list: 1. installation_guide.md 2. legal_information.md 3. releases_info.md ## Expected Behavior & Potential Risk No ## How has this PR been tested?...
## Type of Change feature ## Description Support FP16 for onnxrt adaptor