hotfix: metal has known sync issue

Author: geohot

.github/workflows/benchmark.yml

@@ -82,8 +82,8 @@ jobs:
       run: |
         python3.11 examples/llama.py --gen 1 --prompt "Hello." --count 10 --temperature 0 --timing --quantize int8 | tee llama_int8.txt
         python3.11 examples/llama.py --gen 1 --prompt "Hello." --count 10 --temperature 0 --timing --quantize nf4 | tee llama_nf4.txt
-    - name: Run LLaMA 7B on 4 (virtual) GPUs
-      run: python3.11 examples/llama.py --gen 1 --size 7B --shard 4 --prompt "Hello." --count 10 --temperature 0  --timing | tee llama_four_gpu.txt
+    #- name: Run LLaMA 7B on 4 (virtual) GPUs
+    #  run: python3.11 examples/llama.py --gen 1 --size 7B --shard 4 --prompt "Hello." --count 10 --temperature 0  --timing | tee llama_four_gpu.txt
     - name: Run GPT2
       run: |
         JIT=0 python3.11 examples/gpt2.py --prompt "Hello." --count 10 --temperature 0 --timing | tee gpt2_unjitted.txt