Merge branch 'main' into shortfin-system-selection

.github/workflows/ci_windows_x64-libshortfin.yml

@@ -0,0 +1,95 @@
+# Copyright 2024 Advanced Micro Devices, Inc.
+#
+# Licensed under the Apache License v2.0 with LLVM Exceptions.
+# See https://llvm.org/LICENSE.txt for license information.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+name: CI - shortfin - Windows
+
+on:
+  workflow_dispatch:
+  pull_request:
+  push:
+    branches:
+      - main
+    paths:
+      - '.github/workflows/ci_windows_x64-libshortfin.yml'
+      - 'shortfin/**'
+
+permissions:
+  contents: read
+
+concurrency:
+  # A PR number if a pull request and otherwise the commit hash. This cancels
+  # queued and in-progress runs for the same PR (presubmit) or commit
+  # (postsubmit). The workflow name is prepended to avoid conflicts between
+  # different workflows.
+  group: ${{ github.workflow }}-${{ github.event.number || github.sha }}
+  cancel-in-progress: true
+
+env:
+  IREE_REPO_DIR: ${{ github.workspace }}/iree
+  LIBSHORTFIN_DIR: ${{ github.workspace }}/shortfin/
+
+jobs:
+  build-and-test:
+    name: Build and test
+    runs-on: windows-2022
+
+    steps:
+    - name: Configure MSVC
+      uses: ilammy/msvc-dev-cmd@0b201ec74fa43914dc39ae48a89fd1d8cb592756 # v1.13.0
+
+    - name: Checkout repository
+      uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
+      with:
+        submodules: false
+
+    - name: Checkout IREE repo
+      uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
+      with:
+        repository: iree-org/iree
+        path: ${{ env.IREE_REPO_DIR }}
+        submodules: false
+        ref: candidate-20240904.1006
+
+    - name: Initalize IREE submodules
+      working-directory: ${{ env.IREE_REPO_DIR }}
+      run : |
+        git submodule update --init --depth 1 -- third_party/benchmark
+        git submodule update --init --depth 1 -- third_party/cpuinfo/
+        git submodule update --init --depth 1 -- third_party/flatcc
+        git submodule update --init --depth 1 -- third_party/googletest
+        git submodule update --init --depth 1 -- third_party/hip-build-deps/
+
+    - name: Setup Python
+      uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # v5.1.1
+      with:
+        python-version: "3.12"
+        cache: "pip"
+    - name: Install Python packages
+      working-directory: ${{ env.LIBSHORTFIN_DIR }}
+      run: |
+        pip install -r requirements-tests.txt
+        pip install -r requirements-iree-compiler.txt
+        pip freeze
+
+    - name: Build shortfin (full)
+      working-directory: ${{ env.LIBSHORTFIN_DIR }}
+      shell: bash
+      run: |
+        mkdir build
+        cmake -GNinja \
+          -S. \
+          -Bbuild \
+          -DSHORTFIN_BUNDLE_DEPS=ON \
+          -DSHORTFIN_IREE_SOURCE_DIR="${{ env.IREE_REPO_DIR }}" \
+          -DSHORTFIN_BUILD_PYTHON_BINDINGS=ON
+        cmake --build build --target all
+        pip install -v -e build/
+
+    - name: Test shortfin (full)
+      working-directory: ${{ env.LIBSHORTFIN_DIR }}
+      run: |
+        ctest --timeout 30 --output-on-failure --test-dir build
+        pytest -s

.github/workflows/eval_test.yaml

@@ -0,0 +1,60 @@
+name: Evaluation Tests
+
+on:
+  workflow_dispatch:
+  schedule:
+    # Weekdays nightly at 07:00 UTC = 23:00 PST / 00:00 PDT.
+    - cron: "0 7 * * 1-5"
+
+concurrency:
+  # A PR number if a pull request and otherwise the commit hash. This cancels
+  # queued and in-progress runs for the same PR (presubmit) or commit
+  # (postsubmit). The workflow name is prepended to avoid conflicts between
+  # different workflows.
+  group: ${{ github.workflow }}-${{ github.event.number || github.sha }}
+  cancel-in-progress: true
+
+jobs:
+  test_perplexity:
+    name: "Evaluation Tests - perplexity"
+    strategy:
+      matrix:
+        version: [3.11]
+        os: [ubuntu-latest, windows-latest]
+      fail-fast: false
+    runs-on: ${{matrix.os}}
+    defaults:
+      run:
+        shell: bash
+    env:
+      PIP_CACHE_DIR: "${{ github.workspace }}/.pip-cache"
+    steps:
+      - name: "Setting up Python"
+        id: setup_python
+        uses: actions/setup-python@v3
+        with:
+          python-version: ${{matrix.version}}
+
+      - name: "Checkout Code"
+        uses: actions/checkout@v3
+
+      - name: Cache Pip Packages
+        uses: actions/cache@v4
+        id: cache-pip
+        with:
+          path: ${{ env.PIP_CACHE_DIR }}
+          key: pip-${{ steps.setup_python.outputs.python-version }}-${{ hashFiles('*requirements.txt') }}
+
+      - 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 \
+            -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
+          pip install --no-compile -r requirements.txt -e sharktank/ shortfin/
+
+      - name: Run perplexity test
+        run:  pytest sharktank/tests/evaluate/perplexity_test.py

docs/model_cookbook.md

@@ -257,6 +257,16 @@ iree-run-module \
   --parameters=model=/tmp/open_llama_3b_v2/open-llama-3b-v2-f16.gguf
 ```
 
+## Evaluation pipeline
+
+Run perplexity test:
+
+```bash
+python -m  sharktank.evaluate.perplexity \
+  --gguf-file=llama8b_f16.gguf \
+  --tokenizer-config-json=tokenizer_config.json
+```
+
 ## Generating data for llama models
 
 ```bash

requirements.txt

@@ -7,6 +7,7 @@ onnx==1.15.0
 huggingface-hub==0.22.2
 transformers==4.40.0
 sentencepiece==0.2.0
+datasets==3.0.0
 
 # It is expected that you have installed a PyTorch version/variant specific
 # to your needs, so we only include a minimum version spec.

sharktank/setup.py

@@ -78,11 +78,10 @@ def initialize_options(self):
     name=f"sharktank",
     version=f"{PACKAGE_VERSION}",
     author="SHARK Authors",
-    author_email="[email protected]",
     description="SHARK layers and inference models for genai",
     long_description=README,
     long_description_content_type="text/markdown",
-    url="https://github.com/nod-ai/sharktank",
+    url="https://github.com/nod-ai/SHARK-Platform",
     license="Apache-2.0",
     classifiers=[
         "Development Status :: 3 - Alpha",

sharktank/sharktank/evaluate/data/eval_prompts.txt

@@ -0,0 +1,12 @@
+Robert Boulter is an English film, television and theatre actor.
+Robert Boulter had a guest-starring role on the television series "The Bill" in 2000.
+Du Fu was a prominent Chinese poet of the Tang dynasty.
+Along with Li Bai (Li Po), Du Fu is frequently called the greatest of the Chinese poets.
+The Ise-class battleships were a pair of dreadnought battleships built for the Imperial Japanese Navy (IJN) during World War I.
+Originally intended to be repeats of the preceding Fusō class, the Ise-class battleships were redesigned before construction began. Both ships carried supplies for the survivors of the Great Kantō earthquake in 1923.
+They were modernized in 1934-37 with improvements to their armour and machinery and a rebuilt superstructure in the pagoda mast style. Afterwards they played a minor role in the Second Sino-Japanese War.
+Richard Gale "Dick" Rifenburg (August 21, 1926-December 5, 1994) was an American football player and a pioneering television broadcaster for the forerunner to WIVB-TV in Buffalo.
+Rifenburg played college football for the University of Michigan Wolverines in 1944 and from 1946 to 1948. He was a consensus selection at end on the 1948 College Football All-America Team.
+Rifenburg played professionally in the National Football League (NFL) with the Detroit Lions for one season in 1950. After retiring from football he settled in Buffalo and became a sports broadcaster.
+An oxaziridine is an organic molecule that features a three-membered heterocycle containing oxygen, nitrogen, and carbon. In their largest application, oxazidines are intermediates in the industrial production of hydrazine.
+Oxaziridine derivatives are also used as specialized reagents in organic chemistry for a variety of oxidations, including alpha hydroxylation of enolates, epoxidation and aziridination of olefins, and other heteroatom transfer reactions.