From 3e44c97806ac6221d87b85aa9658321d07cc8581 Mon Sep 17 00:00:00 2001 From: Xiaoyu <85524621+xiaoyu-work@users.noreply.github.com> Date: Tue, 12 Nov 2024 12:34:01 -0800 Subject: [PATCH] Remove static key from quantize cli (#1481) ## Describe your changes `static` quantization is not supported by cli now. Removing `static` key from template. Otherwise, cli doc will have this option. ## Checklist before requesting a review - [ ] Add unit tests for this change. - [ ] Make sure all tests can pass. - [ ] Update documents if necessary. - [ ] Lint and apply fixes to your code by running `lintrunner -a` - [ ] Is this a user-facing change? If yes, give a description of this change to be included in the release notes. - [ ] Is this PR including examples changes? If yes, please remember to update [example documentation](https://github.com/microsoft/Olive/blob/main/docs/source/examples.md) in a follow-up PR. ## (Optional) Issue link --- olive/cli/quantize.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/olive/cli/quantize.py b/olive/cli/quantize.py index ad5bc548a..2837fdc39 100644 --- a/olive/cli/quantize.py +++ b/olive/cli/quantize.py @@ -235,12 +235,12 @@ def run(self): "onnx_model_defaults": {"implementation": "matmul4", "precision": "int4"}, "description": "(OnnxModel) HQQ quantization using onnxruntime.", }, - "static": { - "implementations": ["onnx_static", "inc_static"], - "hf_model_defaults": {"implementation": None, "precision": None}, - "onnx_model_defaults": {"implementation": "onnx_static", "precision": "int8"}, - "description": "(OnnxModel) Static quantization using onnxruntime.", - }, + # "static": { + # "implementations": ["onnx_static", "inc_static"], + # "hf_model_defaults": {"implementation": None, "precision": None}, + # "onnx_model_defaults": {"implementation": "onnx_static", "precision": "int8"}, + # "description": "(OnnxModel) Static quantization using onnxruntime.", + # }, "dynamic": { "implementations": ["onnx_dynamic", "inc_dynamic"], "hf_model_defaults": {"implementation": None, "precision": None},