From 0fad284108f30a09cd7265e842e08810679f06ee Mon Sep 17 00:00:00 2001 From: Mark O'Connor Date: Mon, 3 Jun 2024 12:09:29 +0200 Subject: [PATCH] Update Mixtral perf figures Perf measurements taken with 3bb01f9a7b8a8448c5e8458684a06943739b2c6c --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 0064befa775..42c69e0764b 100644 --- a/README.md +++ b/README.md @@ -56,7 +56,7 @@ | [LLaMA-2-70B-decode](./models/demos/t3000/llama2_70b) | Tensor Parallel | 129th | 32 | 8.5 t/s/u - 272 t/s | 13.9 t/s/u - 445 t/s | 20 t/s/u | | [LLaMA-3-70B-decode](./models/demos/t3000/llama3_70b) | Tensor Parallel | 129th | 32 | 8.1 t/s/u - 257 t/s | 13.9 t/s/u - 445 t/s | 20 t/s/u | | [Falcon40B-decode](./models/demos/t3000/falcon40b) | Tensor Parallel | 129th | 32 | 1.5 t/s/u - 48 t/s | 14.0 t/s/u - 448 t/s | 30 t/s/u | -| [Mixtral7Bx8-decode](./models/demos/t3000/mixtral8x7b) | Tensor Parallel | 129th | 32 | 3.6 t/s/u - 114 t/s | 23.5 t/s/u - 752 t/s | 28 t/s/u | +| [Mixtral7Bx8-decode](./models/demos/t3000/mixtral8x7b) | Tensor Parallel | 129th | 32 | 7.0 t/s/u - 225 t/s | 27.0 t/s/u - 864 t/s | 28 t/s/u | | ResNet50 | Data Parallel | coming soon | | | | | ## Using TT-NN ops and tensors