[sharktank] Update shark-ai CIs with latest install

.github/workflows/ci-llama-large-tests.yaml

@@ -59,21 +59,11 @@ jobs:
       - name: Install pip deps
         run: |
           python -m pip install --no-compile --upgrade pip
-          # Note: We install in three steps in order to satisfy requirements
-          # from non default locations first. Installing the PyTorch CPU
-          # wheels saves multiple minutes and a lot of bandwidth on runner setup.
-          pip install --no-compile -r pytorch-cpu-requirements.txt
-          pip install --no-compile -r requirements.txt -r sharktank/requirements-tests.txt -e sharktank/
-
-          # Install latest iree-turbine.
-          pip install --no-compile -f https://iree.dev/pip-release-links.html --src deps \
-            -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
-
-
-          # Test with nightly releases, not what iree-turbine uses.
+          pip install shark-ai[apps]
+          pip install sharktank -f https://github.com/nod-ai/SHARK-Platform/releases/expanded_assets/dev-wheels --upgrade --pre
           pip install -f https://iree.dev/pip-release-links.html --upgrade --pre \
-            iree-base-compiler \
-            iree-base-runtime
+            iree-base-compiler iree-base-runtime --src deps \
+            -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
 
       - name: Run llama tests
         run: pytest sharktank/tests/models/llama/benchmark_amdgpu_test.py -v -s --run-nightly-llama-tests --iree-hip-target=gfx942 --html=out/llm/llama/benchmark/index.html

.github/workflows/ci-llama-quick-tests.yaml

@@ -59,21 +59,8 @@ jobs:
       - name: Install pip deps
         run: |
           python -m pip install --no-compile --upgrade pip
-          # Note: We install in three steps in order to satisfy requirements
-          # from non default locations first. Installing the PyTorch CPU
-          # wheels saves multiple minutes and a lot of bandwidth on runner setup.
-          pip install --no-compile -r pytorch-cpu-requirements.txt
-          pip install --no-compile -r requirements.txt -r sharktank/requirements-tests.txt -e sharktank/
-
-          # Install latest iree-turbine.
-          pip install --no-compile -f https://iree.dev/pip-release-links.html --src deps \
-            -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
-
-
-          # Test with nightly releases, not what iree-turbine uses.
-          pip install -f https://iree.dev/pip-release-links.html --upgrade --pre \
-            iree-base-compiler \
-            iree-base-runtime
+          pip install shark-ai[apps]
+          pip install sharktank -f https://github.com/nod-ai/SHARK-Platform/releases/expanded_assets/dev-wheels
 
       - name: Run llama 8b f16 decomposed test
         run: pytest sharktank/tests/models/llama/benchmark_amdgpu_test.py -v -s --iree-hip-target=gfx942 --run-quick-llama-test

.github/workflows/ci-sglang-benchmark.yml

@@ -58,21 +58,12 @@ jobs:
       - name: Install pip deps
         run: |
           python -m pip install --no-compile --upgrade pip
-          # Note: We install in three steps in order to satisfy requirements
-          # from non default locations first. Installing the PyTorch CPU
-          # wheels saves multiple minutes and a lot of bandwidth on runner setup.
-          pip install --no-compile -r pytorch-cpu-requirements.txt
-          pip install --no-compile -f https://iree.dev/pip-release-links.html --src deps \
+          pip install shark-ai[apps]
+          pip install sharktank -f https://github.com/nod-ai/SHARK-Platform/releases/expanded_assets/dev-wheels --upgrade --pre
+          pip install shortfin -f https://github.com/nod-ai/shark-ai/releases/expanded_assets/dev-wheels --upgrade --pre
+          pip install -f https://iree.dev/pip-release-links.html --upgrade --pre \
+            iree-base-compiler iree-base-runtime --src deps \
             -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
-          pip install --no-compile -r requirements.txt -e sharktank/ shortfin/
-
-          # Try with the latest nightly releases, not what iree-turbine pins.
-          # We could also pin to a known working or stable version.
-          # This should eventually stabilize. Do the best we can for now.
-          pip install -f https://iree.dev/pip-release-links.html --upgrade \
-            iree-base-compiler==3.0.0rc20241118 \
-            iree-base-runtime==3.0.0rc20241118 \
-            "numpy<2.0"
 
       - name: Install SGLang
         run: pip install "git+https://github.com/nod-ai/sglang.git#subdirectory=python"

.github/workflows/ci-sglang-integration-tests.yml

@@ -59,20 +59,12 @@ jobs:
       - name: Install pip deps
         run: |
           python -m pip install --no-compile --upgrade pip
-          # Note: We install in three steps in order to satisfy requirements
-          # from non default locations first. Installing the PyTorch CPU
-          # wheels saves multiple minutes and a lot of bandwidth on runner setup.
-          pip install --no-compile -r pytorch-cpu-requirements.txt
-          pip install --no-compile -f https://iree.dev/pip-release-links.html --src deps \
+          pip install shark-ai[apps]
+          pip install sharktank -f https://github.com/nod-ai/SHARK-Platform/releases/expanded_assets/dev-wheels --upgrade --pre
+          pip install shortfin -f https://github.com/nod-ai/shark-ai/releases/expanded_assets/dev-wheels --upgrade --pre
+          pip install -f https://iree.dev/pip-release-links.html --upgrade --pre \
+            iree-base-compiler iree-base-runtime --src deps \
             -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
-          pip install --no-compile -r requirements.txt -e sharktank/ shortfin/
-
-          # Use newest possible releases to be able to track commits that may
-          # cause errors.
-          pip install -f https://iree.dev/pip-release-links.html --upgrade \
-            iree-base-compiler \
-            iree-base-runtime \
-            "numpy<2.0"
 
       - name: Install SGLang
         run: pip install "git+https://github.com/nod-ai/sglang.git#subdirectory=python"

.github/workflows/ci-shark-ai.yml

@@ -54,22 +54,9 @@ jobs:
       - name: Install pip deps
         run: |
           python -m pip install --no-compile --upgrade pip
-          # Note: We install in three steps in order to satisfy requirements
-          # from non default locations first. Installing the PyTorch CPU
-          # wheels saves multiple minutes and a lot of bandwidth on runner setup.
-          pip install --no-compile -r pytorch-cpu-requirements.txt
-          pip install --no-compile -r requirements.txt -e sharktank/ shortfin/
-
-          # Install latest iree-tubrine.
-          pip install --no-compile -f https://iree.dev/pip-release-links.html --src deps \
-            -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
-
-          # Try with the latest IREE nightly releases, not what iree-turbine pins.
-          # We could also pin to a known working or stable version.
-          # This should eventually stabilize. Do the best we can for now.
-          pip install -f https://iree.dev/pip-release-links.html --upgrade --pre \
-            iree-base-compiler \
-            iree-base-runtime
+          pip install shark-ai[apps]
+          pip install sharktank -f https://github.com/nod-ai/SHARK-Platform/releases/expanded_assets/dev-wheels
+          pip install shortfin -f https://github.com/nod-ai/shark-ai/releases/expanded_assets/dev-wheels
 
       - name: Run LLM Integration Tests
         run: pytest -v app_tests/integration_tests/llm/shortfin --log-cli-level=INFO

.github/workflows/ci-sharktank.yml

@@ -55,16 +55,8 @@ jobs:
       - name: Install pip deps
         run: |
           python -m pip install --no-compile --upgrade pip
-          # Note: We install in three steps in order to satisfy requirements
-          # from non default locations first. Installing the PyTorch CPU
-          # wheels saves multiple minutes and a lot of bandwidth on runner setup.
-          pip install --no-compile -r pytorch-cpu-requirements.txt
-          pip install --no-compile -r requirements.txt -r sharktank/requirements-tests.txt -e sharktank/
-
-          # Update to the latest iree packages.
-          pip install -f https://iree.dev/pip-release-links.html --upgrade --pre \
-            iree-base-compiler iree-base-runtime --src deps \
-            -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
+          pip install shark-ai[apps]
+          pip install sharktank -f https://github.com/nod-ai/SHARK-Platform/releases/expanded_assets/dev-wheels
 
       - name: Run sharktank tests
         if: ${{ !cancelled() }}
@@ -107,22 +99,8 @@ jobs:
       - name: Install sharktank deps
         run: |
           python -m pip install --no-compile --upgrade pip
-          # Note: We install in three steps in order to satisfy requirements
-          # from non default locations first. Installing the PyTorch CPU
-          # wheels saves multiple minutes and a lot of bandwidth on runner setup.
-          pip install --no-compile -r pytorch-cpu-requirements.txt
-          pip install --no-compile -r requirements.txt -r sharktank/requirements-tests.txt -e sharktank/
-
-          # Install latest iree-tubrine.
-          pip install --no-compile -f https://iree.dev/pip-release-links.html --src deps \
-            -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
-
-          # Try with the latest IREE nightly releases, not what iree-turbine pins.
-          # We could also pin to a known working or stable version.
-          # This should eventually stabilize. Do the best we can for now.
-          pip install -f https://iree.dev/pip-release-links.html --upgrade --pre \
-            iree-base-compiler \
-            iree-base-runtime
+          pip install shark-ai[apps]
+          pip install sharktank -f https://github.com/nod-ai/SHARK-Platform/releases/expanded_assets/dev-wheels
 
       - name: Run tests
         run: |

.github/workflows/ci_eval.yaml

@@ -57,22 +57,11 @@ jobs:
       - name: Install sharktank deps
         run: |
           python -m pip install --no-compile --upgrade pip
-          # Note: We install in three steps in order to satisfy requirements
-          # from non default locations first. Installing the PyTorch CPU
-          # wheels saves multiple minutes and a lot of bandwidth on runner setup.
-          pip install --no-compile -r pytorch-cpu-requirements.txt
-          pip install --no-compile -r requirements.txt -r sharktank/requirements-tests.txt -e sharktank/
-
-          # Install latest iree-tubrine.
-          pip install --no-compile -f https://iree.dev/pip-release-links.html --src deps \
-            -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
-
-          # Try with the latest IREE nightly releases, not what iree-turbine pins.
-          # We could also pin to a known working or stable version.
-          # This should eventually stabilize. Do the best we can for now.
+          pip install shark-ai[apps]
+          pip install sharktank -f https://github.com/nod-ai/SHARK-Platform/releases/expanded_assets/dev-wheels --upgrade --pre
           pip install -f https://iree.dev/pip-release-links.html --upgrade --pre \
-            iree-base-compiler \
-            iree-base-runtime
+            iree-base-compiler iree-base-runtime --src deps \
+            -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
 
       - name: Run perplexity test with IREE
         run:  pytest -n 8 -v -s sharktank/tests/evaluate/perplexity_iree_test.py --run-nightly-llama-tests --bs=100 --iree-device='hip://7' --iree-hip-target=gfx942 --iree-hal-target-backends=rocm --llama3-8b-f16-model-path=/data/llama3.1/8b/llama8b_f16.irpa --llama3-8b-tokenizer-path=/data/llama3.1/8b/tokenizer_config.json --html=out/llm/llama/perplexity/iree_perplexity/index.html
@@ -121,14 +110,10 @@ jobs:
       - name: Install sharktank deps
         run: |
           python -m pip install --no-compile --upgrade pip
-          # Note: We install in three steps in order to satisfy requirements
-          # from non default locations first. Installing the PyTorch CPU
-          # wheels saves multiple minutes and a lot of bandwidth on runner setup.
-          pip install --no-compile -r pytorch-cpu-requirements.txt
-          pip install --no-compile -r requirements.txt -r sharktank/requirements-tests.txt -e sharktank/
-
-          # Install latest iree-tubrine.
-          pip install --no-compile -f https://iree.dev/pip-release-links.html --src deps \
+          pip install shark-ai[apps]
+          pip install sharktank -f https://github.com/nod-ai/SHARK-Platform/releases/expanded_assets/dev-wheels --upgrade --pre
+          pip install -f https://iree.dev/pip-release-links.html --upgrade --pre \
+            iree-base-compiler iree-base-runtime --src deps \
             -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
 
       - name: Run perplexity test with Torch

.github/workflows/ci_eval_short.yaml

@@ -56,22 +56,8 @@ jobs:
       - name: Install sharktank deps
         run: |
           python -m pip install --no-compile --upgrade pip
-          # Note: We install in three steps in order to satisfy requirements
-          # from non default locations first. Installing the PyTorch CPU
-          # wheels saves multiple minutes and a lot of bandwidth on runner setup.
-          pip install --no-compile -r pytorch-cpu-requirements.txt
-          pip install --no-compile -r requirements.txt -r sharktank/requirements-tests.txt -e sharktank/
-
-          # Install latest iree-tubrine.
-          pip install --no-compile -f https://iree.dev/pip-release-links.html --src deps \
-            -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
-
-          # Try with the latest IREE nightly releases, not what iree-turbine pins.
-          # We could also pin to a known working or stable version.
-          # This should eventually stabilize. Do the best we can for now.
-          pip install -f https://iree.dev/pip-release-links.html --upgrade --pre \
-            iree-base-compiler \
-            iree-base-runtime
+          pip install shark-ai[apps]
+          pip install sharktank -f https://github.com/nod-ai/SHARK-Platform/releases/expanded_assets/dev-wheels
 
       - name: Run perplexity test with vmfb
         run:  pytest -n 8 -v -s sharktank/tests/evaluate/perplexity_iree_test.py --bs=5 --iree-device='hip://6' --iree-hip-target=gfx942 --iree-hal-target-backends=rocm --llama3-8b-f16-model-path=/data/llama3.1/8b/llama8b_f16.irpa --llama3-8b-tokenizer-path=/data/llama3.1/8b/tokenizer_config.json