[Migration] Sendnn inference rename (#946)

<!-- markdownlint-disable -->

## Description

This PR updates the `vllm_spyre` package to `sendnn_inference`.

Docs and publication workflows have been updated in preparation to
publish this as `sendnn-inference==2.0.0`

❗❗❗

Breaking configuration changes!
- The plugin name for `VLLM_PLUGINS` is now `sendnn_inference`
- All config options are now `SENDNN_INFERENCE_*`
- The precompiled model parser now expects `sendnn_inference_version`

## Related Issues

Closes #939 

## Test Plan

- CPU unit tests
- Spyre unit tests
- Spot checks with full model integration tests
- Ensure Test PyPI deploy works

## Checklist

- [ ] I have read the [contributing
guidelines](https://docs.vllm.ai/projects/spyre/en/latest/contributing)
- [ ] My code follows the project's code style (run `bash format.sh`)
- [ ] I have added tests for my changes (if applicable)
- [ ] I have updated the documentation (if applicable)
- [ ] My commits include a `Signed-off-by:` line (DCO compliance)

---------

Signed-off-by: Joe Runde <joe@joerun.de>

Author: joerunde

.github/CODEOWNERS

@@ -6,12 +6,12 @@
 # unless a later match takes precedence
 * @joerunde @prashantgupta24
 
-# This lists cover the "core" components of vLLM-Spyre that require careful review
-/vllm_spyre @yannicks1 @tdoublep @nikolaospapandreou @sducouedic
+# This lists cover the "core" components of SenDNN-Inference that require careful review
+/sendnn_inference @yannicks1 @tdoublep @nikolaospapandreou @sducouedic
 
 # TODO: separate code into different packages:
-#   /vllm_spyre/v1/worker/continuous_batching @nikolaospapandreou
-#   /vllm_spyre/v1/worker/static_batching ...
+#   /sendnn_inference/v1/worker/continuous_batching @nikolaospapandreou
+#   /sendnn_inference/v1/worker/static_batching ...
 
 # Tests
 /tests @rafvasq @prashantgupta24 @sducouedic

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,13 +1,13 @@
 name: 🐛 Bug report
-description: Report a bug in vLLM Spyre
+description: Report a bug in SenDNN Inference
 title: "[Bug]: "
 labels: ["bug"]
 
 body:
 - type: markdown
   attributes:
     value: |
-      Before submitting, please search [existing issues](https://github.com/vllm-project/vllm-spyre/issues) to avoid duplicates.
+      Before submitting, please search [existing issues](https://github.com/torch-spyre/sendnn-inference/issues) to avoid duplicates.
 
 - type: textarea
   attributes:

.github/ISSUE_TEMPLATE/config.yml

@@ -2,12 +2,12 @@ blank_issues_enabled: false
 contact_links:
   - name: 📖 Documentation
     url: https://docs.vllm.ai/projects/spyre/
-    about: Read the vLLM Spyre documentation
+    about: Read the SenDNN-Inference documentation
   - name: 💬 Discussions
     url: https://inviter.co/vllm-slack
     about: Ask questions and discuss in the `#sig-spyre` channel.
   - name: 🤝 Contributing Guide
     url: https://docs.vllm.ai/projects/spyre/en/latest/contributing
-    about: Learn how to contribute to vLLM Spyre
+    about: Learn how to contribute to SenDNN-Inference
 
 # Made with Bob

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -1,13 +1,13 @@
 name: 🚀 Feature request
-description: Suggest a new feature for vLLM Spyre
+description: Suggest a new feature for SenDNN Inference
 title: "[Feature]: "
 labels: ["enhancement"]
 
 body:
 - type: markdown
   attributes:
     value: |
-      Before submitting, please search [existing issues](https://github.com/vllm-project/vllm-spyre/issues) to avoid duplicates.
+      Before submitting, please search [existing issues](https://github.com/torch-spyre/sendnn-inference/issues) to avoid duplicates.
 
 - type: textarea
   attributes:
@@ -22,7 +22,7 @@ body:
   attributes:
     label: Motivation and context
     description: |
-      Why is this feature important? How would it benefit vLLM Spyre users?
+      Why is this feature important? How would it benefit SenDNN Inference users?
       
       Is this related to a specific problem or limitation?
   validations:

.github/ISSUE_TEMPLATE/rfc.yml

@@ -1,13 +1,13 @@
 name: 💭 Request for comments
-description: Start a discussion for larger changes related to vLLM Spyre
+description: Start a discussion for larger changes related to SenDNN Inference
 title: "[RFC]: "
 labels: []
 
 body:
 - type: markdown
   attributes:
     value: |
-      Before submitting, please search [existing issues](https://github.com/vllm-project/vllm-spyre/issues) to avoid duplicates.
+      Before submitting, please search [existing issues](https://github.com/torch-spyre/sendnn-inference/issues) to avoid duplicates.
 
 - type: textarea
   attributes:

.github/workflows/build_and_publish.yaml

@@ -1,12 +1,12 @@
-name: Build and Publish vllm-spyre Library
+name: Build and Publish sendnn-inference Library
 
 on:
   release:
     types: [published]
 
 jobs:
   build:
-    # Only run for vllm-spyre releases (v* tags).
+    # Only run for sendnn-inference releases (v* tags).
     if: startsWith(github.ref, 'refs/tags/v')
     runs-on: ubuntu-latest
 

.github/workflows/build_docker.yml

@@ -1,23 +1,8 @@
 name: "Build Docker"
 
+# Manual dispatch only for now
 on:
   workflow_dispatch:
-  push:
-    branches:
-      - "main"
-    paths-ignore:
-      - "**.md"
-  pull_request:
-    branches:
-      - "main"
-    paths:
-      - ".github/workflows/build_docker.yml"
-      - "docker/**"
-      - "vllm_spyre/**/*.py"
-      - "pyproject.toml"
-      - "uv.lock"
-  release:
-    types: [published]
 
 defaults:
   run:
@@ -27,8 +12,8 @@ jobs:
   build:
     runs-on: ubuntu-latest
     env:
-      CACHE_IMAGE: "ghcr.io/vllm-project/vllm-spyre:build-cache"
-      QUAY_REPOSITORY: "quay.io/ibm-aiu/vllm-spyre"
+      CACHE_IMAGE: "ghcr.io/torch-spyre/sendnn-inference:build-cache"
+      QUAY_REPOSITORY: "quay.io/ibm-aiu/sendnn-inference"
 
     permissions:
       packages: write
@@ -38,7 +23,7 @@ jobs:
     - name: "Checkout"
       uses: actions/checkout@v4
       # We need to fetch history and tags so that we can correctly version the
-      # vllm_spyre package, since it uses setuptools_scm to version based on
+      # sendnn-inference package, since it uses setuptools_scm to version based on
       # git tags.
       with:
         fetch-depth: 0

.github/workflows/publish_to_test_pypi.yaml

@@ -1,4 +1,4 @@
-# This tests the publication process for vllm-spyre by pushing a pre-release to test.pypi.org
+# This tests the publication process for sendnn-inference by pushing a pre-release to test.pypi.org
 # on all main commits
 name: Test publication on test.pypi.org
 
@@ -13,7 +13,7 @@ jobs:
 
     environment:
       name: testpypi
-      url: https://test.pypi.org/p/vllm-spyre
+      url: https://test.pypi.org/p/sendnn-inference
     permissions:
       id-token: write  # IMPORTANT: this permission is mandatory for trusted publishing
 

.github/workflows/test.yml

@@ -18,7 +18,7 @@ env:
   FORCE_COLOR: "1"
   VLLM_CPU_DISABLE_AVX512: "true"
   VLLM_TARGET_DEVICE: "empty"
-  VLLM_PLUGINS: "spyre"
+  VLLM_PLUGINS: "sendnn_inference"
   HF_HUB_CACHE: "${{ github.workspace }}/.cache/huggingface/hub"
   DEFAULT_HF_MODEL: "ibm-ai-platform/micro-g3.3-8b-instruct-1b"
   DEFAULT_HF_MODEL_REV: "6e9c6465a9d7e5e9fa35004a29f0c90befa7d23f"
@@ -131,8 +131,8 @@ jobs:
             pyproject.toml
             uv.lock
             tests/**/*.py
-            vllm_spyre/**/*.py
-            vllm_spyre/config/model_configs.yaml
+            sendnn_inference/**/*.py
+            sendnn_inference/config/model_configs.yaml
 
       - name: "Install uv"
         if: steps.changed-src-files.outputs.any_changed == 'true'
@@ -159,7 +159,7 @@ jobs:
 
           # Syncs both the runtime and dev deps, based on the lockfile contents
           uv sync --frozen
-          # Builds and installs the vllm_spyre wheel into .venv
+          # Builds and installs the sendnn-inference wheel into .venv
           # This needs to be done after `uv sync`, or the wheel install will be
           # overwritten.
           uv pip install -v .
@@ -260,15 +260,15 @@ jobs:
           MASTER_PORT: 12355
           MASTER_ADDR: localhost
           DISTRIBUTED_STRATEGY_IGNORE_MODULES: WordEmbedding
-          VLLM_SPYRE_TEST_MODEL_LIST: ""
+          SENDNN_INFERENCE_TEST_MODEL_LIST: ""
           HF_HUB_OFFLINE: 1
         run: |
           # Delete the source code so we can ensure we're testing the installed
           # wheel
-          rm -fr vllm_spyre
+          rm -fr sendnn_inference
           # We activate .venv manually and run pytest directly instead of using
           # `uv run`, to avoid having `uv run` re-sync any dependencies or
-          # re-install the vllm_sypre package from source
+          # re-install the sendnn-inference package from source
           source .venv/bin/activate
 
           ${{matrix.test_suite.env_overrides}} python3 -m pytest ${{ matrix.test_suite.flags }} \

.pre-commit-config.yaml

@@ -37,7 +37,7 @@ repos:
   hooks:
     - id: ty
       name: ty check
-      entry: uvx ty@0.0.16 check vllm_spyre
+      entry: uvx ty@0.0.16 check sendnn_inference
       # `system` here instead of python so that we avoid running inside an isolated venv created by
       # prek, and instead have access to the .venv created by uv for the project
       language: system