From 3a628891ab6473f9b3f052ff5fe3d19bacbae413 Mon Sep 17 00:00:00 2001 From: Pleaplusone <38376071+ganyi1996ppo@users.noreply.github.com> Date: Wed, 30 Apr 2025 16:51:56 +0800 Subject: [PATCH] [Feature] Add quant description file for new quant model generated by modelslim (#719) ### What this PR does / why we need it? After discussed with MindStudio about the quantization model format, we decide to support another quant format which may used in new modelslim tool, in which case, `quantization_config` may be removed from the `config.json` file and `quant_model_description.json` will be used for quantization configuration. ### Does this PR introduce _any_ user-facing change? Yes, using the latest quantization format ### How was this patch tested? Test locally Signed-off-by: ganyi --- vllm_ascend/quantization/quant_config.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm_ascend/quantization/quant_config.py b/vllm_ascend/quantization/quant_config.py index adedaa7..22b61f2 100644 --- a/vllm_ascend/quantization/quant_config.py +++ b/vllm_ascend/quantization/quant_config.py @@ -67,7 +67,7 @@ class AscendQuantConfig(QuantizationConfig): @classmethod def get_config_filenames(cls) -> List[str]: - return [] + return ["quant_model_description.json"] @classmethod def from_config(cls, config: Dict[str, Any]) -> "AscendQuantConfig":