From 2bfa234f05ec4c738f62067b5f5ea5f703b8e9f5 Mon Sep 17 00:00:00 2001
From: Casper <casperbh.96@gmail.com>
Date: Thu, 2 Nov 2023 19:28:15 +0100
Subject: [PATCH] Benchmark info (#138)

---
 README.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/README.md b/README.md
index 5e40f1f5..ca631ef5 100644
--- a/README.md
+++ b/README.md
@@ -197,6 +197,9 @@ generation_output = model.generate(
 
 ## Benchmarks
 
+- GPU: RTX 3090
+- Command: `python examples/benchmark --model_path <hf_model>`
+
 | Model Name    | Version | Batch Size | Prefill Length | Decode Length | Prefill tokens/s | Decode tokens/s | Memory (VRAM)    |
 |---------------|---------|------------|----------------|---------------|------------------|-----------------|------------------|
 | Vicuna 7B     | GEMM    | 1          | 64             | 64            | 2618.88          | 125.428         | 4.57 GB (19.31%) |