update cpu benchmark

bitsandbytes-foundation · Sep 12, 2024 · 6eff85c · 6eff85c
1 parent e959717
commit 6eff85c
Showing 1 changed file with 7 additions and 7 deletions.
diff --git a/docs/source/non_cuda_backends.mdx b/docs/source/non_cuda_backends.mdx
@@ -24,17 +24,17 @@ Thank you for your support!
 
 ### Intel
 
-The following performance data is collected from Intel 4th Gen Xeon (SPR) platform. The tables show latency and memory compared with different data types of [Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf).
+The following performance data is collected from Intel 4th Gen Xeon (SPR) platform. The tables show speed-up and memory compared with different data types of [Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf).
 
 For inference:
-|         | BF16   | INT8   | NF4   | FP4   |
-| latency | 1.0x   | 0.62x  | 2.43x | 0.02x |
-| memory  | 13.1G  | 7.2G   | 5.7G  | 4.6G  |
+|          | BF16   | INT8   | NF4   | FP4   |
+| speed-up | 1.0x   | 0.6x   | 2.3x  | 0.03x |
+| memory   | 13.1G  | 7.6G   | 5.0G  | 4.6G  |
 
 For fine-tune:
-|               | BF16   | INT8   | NF4   | FP4   |
-| time-to-train | 1.0x   | 0.36x  | 0.07x | 0.07x |
-| memory        | 40G    | 8.6G   | 5.2G  | 5.2G  |
+|          | AMP BF16   | INT8   | NF4   | FP4   |
+| speed-up | 1.0x       | 0.38x  | 0.07x | 0.07x |
+| memory   | 40G        | 9G     | 6.6G  | 6.6G  |
 
 
 ### AMD