From 4e570a99a705502948c29519bebff9fb43ea079b Mon Sep 17 00:00:00 2001
From: iamvalenciia <val22018@byui.edu>
Date: Fri, 14 Feb 2025 03:09:07 -0500
Subject: [PATCH] Fix incorrect comment in linear function regarding
 weight.element_size()

---
 inference/model.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/inference/model.py b/inference/model.py
index 40bbf4d..e56f599 100644
--- a/inference/model.py
+++ b/inference/model.py
@@ -143,8 +143,8 @@ 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 
-          is used for computation.
+        - If `weight` is in a higher precision format (e.g., float32 or bfloat16), then `element_size() > 1`, and the original
+          weight tensor 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.
     """