From 5552dfc629375aeed898a685188a98295b00a22d Mon Sep 17 00:00:00 2001 From: Anindyadeep Date: Thu, 7 Dec 2023 20:09:46 +0000 Subject: [PATCH] added the benchmarking resuls on cuda --- docs/llama2.md.template | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/llama2.md.template b/docs/llama2.md.template index fe9eb667..468e2f58 100644 --- a/docs/llama2.md.template +++ b/docs/llama2.md.template @@ -17,6 +17,7 @@ | tinygrad | - | 20.32 ± 0.06 | - | - | | onnx | - | 54.16 ± 3.15 | - | - | | transformers (pytorch) | 0.44 ± 0.44 | 0.44 ± 0.44 | - | - | +| exllamav2 | - | - | 163.41 ± 5.58 | 120.17 ± 0.73 | *(Data updated: ``)