amd/RyzenAI-SW
51.2
Adequate · 17 November 2026
21.9k
lines of production code
Python
with C++
1
measurement over time
What this system is
Behavioural changes
12 commits (0 fixes) modifying utilities
A change to existing behaviour in utilities — 12 commits, 7 files: “Release V1.3”; “RAI 1.7.0 Release”; “Updates to NPU utils for RAI 1.5.0 release”; and 6 more.
utilities · medium confidence · unverified
12 commits (4 fixes) modifying example/multi-model
A change to existing behaviour in example/multi-model — 12 commits (4 fixs), 123 files: “Release V1.2.0”; “update the readme”; “Release V1.3”; and 4 more.
example/multi-model · medium confidence · unverified
13 commits (2 fixes) modifying demo/multi-model-exec
A change to existing behaviour in demo/multi-model-exec — 13 commits (2 fixs), 21 files: “updates to add one line description for the commands”; “update multi-model demo readme”; “adding links for the multi-model building instructions”; and 6 more.
demo/multi-model-exec · medium confidence · unverified
18 commits (2 fixes) modifying example/transformers
A change to existing behaviour in example/transformers — 18 commits (2 fixs), 3493 files: “merge changes from VitisAI/dev”; “Release V1.2.0”; “removing the --help instructions from llm onnx flow”; and 9 more.
example/transformers · medium confidence · unverified
19 commits (0 fixes) modifying tutorial/hello\_world
A change to existing behaviour in tutorial/hello\_world — 19 commits, 5 files: “Updates for RAI 1.6.0 Release”; “Release V1.2.0”; “Update tutorial/hello\_world/hello\_world.py”; and 9 more.
_tutorial/hello\world · medium confidence · unverified
2 commits (0 fixes) modifying (repo-wide)
A change to existing behaviour in (repo-wide) — 2 commits, 322 files: “Release V1.2.0”; “Release V1.3”.
(repo-wide) · medium confidence · unverified
2 commits (0 fixes) modifying (repo-wide)
A change to existing behaviour in (repo-wide) — 2 commits, 405 files: “Release V1.2.0”; “Release V1.4.0”.
(repo-wide) · medium confidence · unverified
20 commits (0 fixes) modifying CNN-examples
A change to existing behaviour in CNN-examples — 20 commits, 208 files: “RAI 1.7.0 Release”; “RAI 1.9 Release”; “Add Nemotron OCR V2 example with LFS support”; and 11 more.
CNN-examples · medium confidence · unverified
33 commits (4 fixes) modifying onnx-benchmark
A change to existing behaviour in onnx-benchmark — 33 commits (4 fixs), 5 files: “typo”; “Updates for RAI 1.6.0 Release”; “update to onnx-benchmark to support STX and PHX”; and 14 more (refs \#95).
onnx-benchmark · medium confidence · unverified
5 commits (0 fixes) modifying Transformer-examples
A change to existing behaviour in Transformer-examples — 5 commits, 21 files: “RAI 1.9 Release”; “Update run\_inference.py”; “RAI 1.7.0 Release”.
Transformer-examples · medium confidence · unverified
5 commits (0 fixes) modifying WinML
A change to existing behaviour in WinML — 5 commits, 86 files: “updating the LLM readme”; “RAI 1.9 Release”; “RAI 1.8.0 Release”; and 1 more.
WinML · medium confidence · unverified
5 commits (0 fixes) modifying example/yolov8
A change to existing behaviour in example/yolov8 — 5 commits, 49 files: “cleanup yolov8 example”; “Release V1.2.0”; “updates to merge changes from dev to main branch”.
example/yolov8 · medium confidence · unverified
5 commits (0 fixes) modifying iGPU
A change to existing behaviour in iGPU — 5 commits, 6 files: “Update README”; “Release V1.2.0”; “Update README.md”.
iGPU · medium confidence · unverified
5 commits (0 fixes) modifying tutorial/getting\_started\_resnet
A change to existing behaviour in tutorial/getting\_started\_resnet — 5 commits, 12 files: “Release V1.2.0”; “Release V1.3”; “removing the optional configuration option”; and 2 more.
_tutorial/getting\_started\resnet · medium confidence · unverified
5 commits (0 fixes) modifying tutorial/yolov8\_e2e, tutorial/yolov8\_e2e/code/build
A change to existing behaviour in tutorial/yolov8\_e2e, tutorial/yolov8\_e2e/code/build — 5 commits, 420 files: “Updating the yolov8 example for the 1.2 release”; “Release V1.2.0”; “updates to merge changes from dev to main branch”.
_tutorial/yolov8\_e2e, tutorial/yolov8\e2e/code/build · medium confidence · unverified
6 commits (0 fixes) modifying LLM-examples
A change to existing behaviour in LLM-examples — 6 commits, 166 files: “RAI 1.9 Release”; “RAI 1.7.0 Release”; “RAI 1.8.0 Release”.
LLM-examples · medium confidence · unverified
7 commits (0 fixes) modifying Demos
A change to existing behaviour in Demos — 7 commits, 54 files: “RAI 1.9 Release”; “adding Parakeet-TDT example”; “RAI 1.7.0 Release”; and 3 more.
Demos · medium confidence · unverified
7 commits (0 fixes) modifying onnx-benchmark/models
A change to existing behaviour in onnx-benchmark/models — 7 commits, 3 files: “update to onnx-benchmark to support STX and PHX”; “Release V1.2.0”; “updates to onnx-benchmark to support STX and PHX”; and 1 more.
onnx-benchmark/models · medium confidence · unverified
Test coverage
2 commits adding/updating tests in example/transformers/ext/llama.cpp/examples/server/tests/features/steps
Test coverage in example/transformers/ext/llama.cpp/examples/server/tests/features/steps — 2 commits, 1 file: “Release V1.2.0”; “Release V1.4.0”.
example/transformers/ext/llama.cpp/examples/server/tests/features/steps · high confidence · unverified
Dependencies
17 commits updating dependencies (67 manifests)
A dependency / build maintenance change in (dependencies) — 17 commits, 67 files: “RAI 1.9 Release”; “Release V1.2.0”; “adding Parakeet-TDT example”; and 7 more.
(dependencies) · medium confidence · unverified
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
How this codebase got here
Baseline
- First survey — no prior run to compare against. CAI 51.2.
Lenses
- Code Health 61.4
- Architecture 99.7
- Maturity 55.7
- Readiness 32.8
- Security 87.0
- Performance 100.0
Changes since last survey
- 267 commits — 255 feature/other, 12 fixes
By area
- (repo) — 102 commits
- onnx-benchmark/README.md — 14 commits
- tutorial/hello_world — 13 commits
- tutorial/yolov8 — 11 commits
- (root) — 10 commits
- example/llm — 10 commits
- example/transformers — 10 commits
- CNN-examples/Nemotron-OCR-V2 — 9 commits
- demo/multi-model-exec — 9 commits
- iGPU/getting_started — 8 commits
- example/multi-model — 6 commits
- tutorial/object_detection — 6 commits
- Ryzen-AI-CVML-Library/windows — 5 commits
- .github/workflows — 4 commits
- Ryzen-AI-CVML-Library/linux — 4 commits
- demo/ASR — 4 commits
- tutorial/getting_started_resnet — 4 commits
- tutorial/yolov8_e2e — 4 commits
- utilities/npu_check — 4 commits
- CNN-examples/object_detection — 3 commits
Notable commits
- fix: Fix CVML Linux libs
- fix: Fix CVML Linux symlinks
- fix: Fix CVML Linux symlinks
- fix: fix driver instructions
- fix: fix for the build for windows
- fix: fix for the build for windows
- fix: fix to https://github.com/onnx/onnx/issues/6267
- fix: fix to https://github.com/onnx/onnx/issues/6267
- fix: fixes for the multi-model-exec demo
- fix: fixes for the multi-model-exec demo
- fix: update cmakelist.txt to fixed compile issue OPENCV_DIR is add
- fix: update cmakelist.txt to fixed compile issue OPENCV_DIR is add
- change: Add DeepSeek-R1-Distill CPU examples
- change: Add LLM examples
- change: Add Nemotron OCR V2 example with LFS support
- change: Add audio example
- change: Adding ASR demo with OpenAI Whisper
- change: Adding RAG-OGA example
- change: Adding cpp files for igpu example
- change: Fuse additional optimizations
- …and 247 more
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
Survey your own repository
amd/RyzenAI-SW was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.
About this page
- The score is its most recent published measurement, taken on 17 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
- Measured at commit 09a18d01bd14ea95bd66a4647590436f9c1ae8c3 — the exact code this score is about.
- Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
- Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.85+preprod-eba6548ac50f.