add more gpt2 variant in mac/nvidia benchmark (#3599)

tinygrad · Mar 3, 2024 · 8e5d60a · 8e5d60a
1 parent 968d109
commit 8e5d60a
Showing 1 changed file with 8 additions and 1 deletion.
diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
@@ -46,6 +46,10 @@ jobs:
       run: |
         JIT=0 python3 examples/gpt2.py --prompt "Hello." --count 10 --temperature 0 --timing | tee gpt2_unjitted.txt
         JIT=1 python3 examples/gpt2.py --prompt "Hello." --count 10 --temperature 0 --timing | tee gpt2_jitted.txt
+    - name: Run GPT2 w HALF
+      run: JIT=1 HALF=1 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half.txt
+    - name: Run GPT2 w HALF/BEAM
+      run: JIT=1 HALF=1 BEAM=2 CACHELEVEL=0 CAST_BEFORE_VIEW=0 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half_beam.txt
     - name: Run 10 CIFAR training steps
       run: STEPS=10 python3 examples/hlb_cifar10.py | tee train_cifar.txt
     # TODO: this is flaky too
@@ -63,6 +67,8 @@ jobs:
           llama_jitted.txt
           gpt2_unjitted.txt
           gpt2_jitted.txt
+          gpt2_half.txt
+          gpt2_half_beam.txt
           matmul.txt
           matmul_half.txt
           sd.txt
@@ -92,7 +98,7 @@ jobs:
         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
+      run: CUDA=1 JIT=1 HALF=1 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half.txt
     - name: Run GPT2 w HALF/BEAM
       run: CUDA=1 JIT=1 HALF=1 BEAM=2 CACHELEVEL=0 CAST_BEFORE_VIEW=0 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half_beam.txt
     - uses: actions/upload-artifact@v4
@@ -104,6 +110,7 @@ jobs:
           matmul.txt
           gpt2_unjitted.txt
           gpt2_jitted.txt
+          gpt2_half.txt
           gpt2_half_beam.txt
 
   testamdbenchmark: