From e7f5fada32a7d411081e1e36b4125c5e38942c28 Mon Sep 17 00:00:00 2001
From: KokerZhou <111279477+KokerZhou@users.noreply.github.com>
Date: Mon, 23 Mar 2026 16:38:39 +0800
Subject: [PATCH] Update CANN.md to include BF16 support

Added BF16 support information to the CANN documentation and corrected formatting for the installation instructions.
---
 docs/backend/CANN.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/docs/backend/CANN.md b/docs/backend/CANN.md
index 20a7e6fe07..6c1590634f 100755
--- a/docs/backend/CANN.md
+++ b/docs/backend/CANN.md
@@ -161,6 +161,7 @@ lspci -n | grep -Eo '19e5:d[0-9a-f]{3}' | cut -d: -f2
 | FP16                   | Support | Support |
 | Q8_0                   | Support | Partial |
 | Q4_0                   | Support | Partial |
+| BF16                   | Support |         |
 
 > **310P note**
 > - `Q8_0`: data transform / buffer path is implemented, and `GET_ROWS` is supported, but quantized `MUL_MAT` / `MUL_MAT_ID` are not supported.
@@ -230,7 +231,7 @@ docker run --name llamacpp \
 
 3. **Install CANN (driver + toolkit)**
 
-    > The `Ascend-cann` package includes both the driver and toolkit.  
+    > The `Ascend-cann` package includes both the driver and toolkit. 
     > `$ARCH` can be `x86_64` or `aarch64`, `$CHIP` can be `910b` or `310p`.
 
     ```sh