From 5ee97a83f0457d0d805b862aeb387358e1801e6d Mon Sep 17 00:00:00 2001
From: Xingkai Yu <38156925+GeeeekExplorer@users.noreply.github.com>
Date: Fri, 7 Feb 2025 16:42:55 +0800
Subject: [PATCH] fix comment

---
 inference/model.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/inference/model.py b/inference/model.py
index 2ec1b20..40bbf4d 100644
--- a/inference/model.py
+++ b/inference/model.py
@@ -143,7 +143,7 @@ def linear(x: torch.Tensor, weight: torch.Tensor, bias: Optional[torch.Tensor] =
         quantization-aware computations depending on the input parameters.
 
     Notes:
-        - If `weight` is quantized (e.g., `element_size() > 1`), a dequantized version 
+        - If `weight` is quantized (e.g., `element_size() == 1`), a dequantized version 
           is used for computation.
         - If `gemm_impl == "bf16"`, dequantization and a `bf16` GEMM operation are applied.
         - For other cases, the function applies quantization to `x` and uses `fp8_gemm` for computation.