From 52c93e0d73243e1fe80c5f053cfd0cd2e54f438b Mon Sep 17 00:00:00 2001 From: Erjan K Date: Tue, 2 Dec 2025 20:00:10 +0100 Subject: [PATCH] Fix readme typo --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 274182a..29b0a26 100644 --- a/README.md +++ b/README.md @@ -215,7 +215,7 @@ CUDA_VISIBLE_DEVICES=0,1 python run.py --method latent_mas --model_name Qwen/Qwe > vLLM does **not** officially support modifying KV-cache or prompting via latent embeddings. > We modify the partial inner package inside vLLM backend for our method implementation. -> Note minor numeric differences may arise compared to offical HF backend due to different decoding (generation) strategies. Please Use the HF backend to reproduce the official published results. +> Note minor numeric differences may arise compared to official HF backend due to different decoding (generation) strategies. Please Use the HF backend to reproduce the official published results. ## 📚 Citation