From 80bba578125e91a12826eea0d533b776b4a77b82 Mon Sep 17 00:00:00 2001 From: GitHub Actions Date: Mon, 29 Apr 2024 12:05:13 +0000 Subject: [PATCH] Update placeholder in llama2.md and README.md --- README.md | 2 +- docs/llama2.md | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 8c70afe..5e6514d 100644 --- a/README.md +++ b/README.md @@ -50,7 +50,7 @@ Take a first glance of Llama-2-7B Model Performance Metrics Across Different Pre | [Nvidia TensorRT-LLM](/bench_tensorrtllm/) | 55.19 ± 1.03 | 85.03 ± 0.62 | 167.66 ± 2.05 | 235.18 ± 3.20 | -*(Data updated: `17th April 2024`) +*(Data updated: `29th April 2024`) diff --git a/docs/llama2.md b/docs/llama2.md index 624a798..4583875 100644 --- a/docs/llama2.md +++ b/docs/llama2.md @@ -5,7 +5,7 @@ **Environment:** - Model: Llama 2 7B Chat - CUDA Version: 12.1 -- Command: `./benchmark.sh --repetitions 10 --max_tokens 512 --device cuda --prompt 'Write an essay about the transformer model architecture'` +- Command: `./benchmark.sh --repetitions 10 --max_tokens 512 --device cuda --model llama --prompt 'Write an essay about the transformer model architecture'` **Performance Metrics:** (unit: Tokens / second) @@ -27,7 +27,7 @@ | [Nvidia TensorRT-LLM](/bench_tensorrtllm/) | 55.19 ± 1.03 | 85.03 ± 0.62 | 167.66 ± 2.05 | 235.18 ± 3.20 | -*(Data updated: `17th April 2024`) +*(Data updated: `29th April 2024`) ## M2 MAX 32GB Inference Bench: @@ -58,4 +58,4 @@ | [llama.cpp](/bench_llamacpp/) | - | - | 30.11 ± 0.45 | 44.27 ± 0.12 | | [ctransformers](/bench_ctransformers/) | - | - | 20.75 ± 0.36 | 34.04 ± 2.11 | -*(Data updated: `17th April 2024`) +*(Data updated: `29th April 2024`)