From 2a48f4af8cdccf6cf4c2b82db6ab0e066259aa81 Mon Sep 17 00:00:00 2001 From: ADou Date: Wed, 9 Sep 2026 09:20:16 +0000 Subject: [PATCH] [None][docs] drop deleted lm_eval_ad.py from auto_deploy README The AutoDeploy LM Evaluation Harness example script was removed in #7233; the README still documented `python lm_eval_ad.py`, which 404s on main. Signed-off-by: ADou --- examples/auto_deploy/README.md | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/examples/auto_deploy/README.md b/examples/auto_deploy/README.md index 343ad8c87f35..8cdf46239b7b 100644 --- a/examples/auto_deploy/README.md +++ b/examples/auto_deploy/README.md @@ -92,18 +92,6 @@ The script supports flexible configs: The default level is `INFO`. -### Model Evaluation with LM Evaluation Harness - -lm-evaluation-harness is supported. To run the evaluation, please use the following command: - -```bash -# model is defined the same as above. Other config args can also be specified in the model_args (comma separated). -# You can specify any tasks supported with lm-evaluation-harness. -cd examples/auto_deploy -python lm_eval_ad.py \ ---model autodeploy --model_args model=meta-llama/Meta-Llama-3.1-8B-Instruct,world_size=2 --tasks mmlu -``` - ### Mixed-precision Quantization using Model Optimizer Model Optimizer [AutoQuantize](https://nvidia.github.io/Model-Optimizer/reference/generated/modelopt.torch.quantization.model_quant.html#modelopt.torch.quantization.model_quant.auto_quantize) algorithm is a PTQ algorithm from ModelOpt which quantizes a model by searching for the best quantization format per-layer while meeting the performance constraint specified by the user. This way, `AutoQuantize` enables to trade-off model accuracy for performance. @@ -339,4 +327,4 @@ the current progress in AutoDeploy and where you can help. ## Disclaimer This project is under active development and is currently released as beta feature. The code is -subject to change, and may include backward-incompatible updates. +subject to change, and may include backward-incompatible updates. \ No newline at end of file