From 4e2a92cee1bef14d155a269f5417c326f10a54da Mon Sep 17 00:00:00 2001
From: chenyu <chenyu@fastmail.com>
Date: Sun, 17 Dec 2023 02:24:55 -0500
Subject: [PATCH] run HALF GPT2 in nvidia benchmark in addition to HALF/BEAM
 (#2811)

easier to separate the issue between HALF and BEAM when it failed
---
 .github/workflows/benchmark.yml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
index 85fde8e41d..2c5791f942 100644
--- a/.github/workflows/benchmark.yml
+++ b/.github/workflows/benchmark.yml
@@ -81,6 +81,8 @@ jobs:
       run: |
         CUDA=1 JIT=0 python3 examples/gpt2.py --prompt "Hello." --count 10 --temperature 0 --timing | tee gpt2_unjitted.txt
         CUDA=1 JIT=1 python3 examples/gpt2.py --prompt "Hello." --count 10 --temperature 0 --timing | tee gpt2_jitted.txt
+    - name: Run GPT2 w HALF
+      run: CUDA=1 JIT=1 HALF=1 python3 examples/gpt2.py --count 10 --temperature 0 --timing
     - name: Run GPT2 w HALF/BEAM
       run: CUDA=1 JIT=1 HALF=1 BEAM=4 CACHELEVEL=0 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half_beam.txt
     - uses: actions/upload-artifact@v3