test speed llama (#1046)

* test speed llama

* oops, put it back

* uses the real device codegen

* just do it on the mac

* pp

* is faster?

* Revert "is faster?"

This reverts commit 42db542010.

* disable docker again for less load on CI

.github/workflows/test.yml

@@ -207,16 +207,18 @@ jobs:
         python-version: 3.11
     - name: Install Dependencies
       run: pip install -e '.[metal,testing]'
+    - name: Test LLaMA compile speed
+      run: PYTHONPATH="." METAL=1 python3 test/external/external_test_speed_llama.py
     #- name: Run dtype test
     #  run: DEBUG=4 METAL=1 python -m pytest test/test_dtype.py
     - name: Run ops test
       run: DEBUG=2 METAL=1 python -m pytest test/test_ops.py
     # dtype test has issues on test_half_to_int8
 
-  # disabled, this test is flaky
   testdocker:
     name: Docker Test
     runs-on: ubuntu-latest
+    if: ${{ false }}
 
     steps:
     - name: Checkout Code