ov-write-transformations

Write or review OpenVINO ov::Model graph transformations (passes: MatcherPass, ModelPass, GraphRewrite, BackwardGraphRewrite). Use when the user asks to write, add, or refactor a transformation/fusion/decomposition pass, choose between MatcherPass and ModelPass, write pattern-matching predicates, or bring an existing pass in line with OpenVINO transformation conventions.

Zur Installation springen Dateien prüfen

Repository: openvinotoolkit/openvino
Letzte Quellaktivität: 6. Oktober 2026 um 11:37
Erkannte Sprache von SKILL.md: Englisch
Sterne: 11.007
Forks: 3.458

Installationsoptionen

Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.

Mit einem KI-Assistenten installieren

Diesen Prompt kopieren und in den verwendeten KI-Assistenten einfügen.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/openvinotoolkit/openvino/tree/master/.claude/skills/ov-write-transformations.

Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.

npx skills add https://github.com/openvinotoolkit/openvino --skill ov-write-transformations

Der Befehl bleibt in einer Zeile. Scrollen Sie horizontal, um ihn vor dem Kopieren vollständig zu prüfen.

Sie bevorzugen eine lokale Kopie? Laden Sie die Dateien herunter, die SkillsMP derzeit vorliegen.

Quelldateien prüfen

Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.

SKILL.md

Quellanweisungen · Schreibgeschützte Vorschau

name: ov-write-transformations
description: Write or review OpenVINO ov::Model graph transformations (passes: MatcherPass, ModelPass, GraphRewrite, BackwardGraphRewrite). Use when the user asks to write, add, or refactor a transformation/fusion/decomposition pass, choose between MatcherPass and ModelPass, write pattern-matching predicates, or bring an existing pass in line with OpenVINO transformation conventions.

1. Read [src/common/transformations/docs/writing_transformations.md](../../../src/common/transformations/docs/writing_transformations.md) — it covers where transformations live, choosing the pass type, anatomy of a MatcherPass, pattern matching and predicates, writing the callback, modifying the graph, documenting the pass, and what NOT to do. 2. Try to find an existing transformation that can be extended to cover the new pattern. 3. Write or modify the pass following the patterns in that guide. 4. Add tests using the `ov-transformation-tests` skill, then build and run them to ensure the pass compiles and behaves as expected.

Auf GitHub ansehen

Zurück zur Suche Zurück zur Installation

ov-gguf

Develop and troubleshoot the OpenVINO GGUF frontend (src/frontends/gguf) and the llama.cpp ggml-openvino backend that uses it. Use when checking whether a .gguf or mmproj model is supported; when a .gguf file is rejected as an unsupported architecture; when enabling a llama.cpp model family (llama, qwen, gemma, phi, MoE, hybrid/recurrent) through arch_registry, DecoderBuilder, a ModelBuilder or an ArchitectureExtension; when adding a vision/audio projector or ProjectorExtension; when conversion fails with "Translation for operation type GGML_OP_* is not implemented" or an op translator/op_case in src/op/ needs work; when making a converted model stateful or GenAI/PagedAttention-ready; or when a GGUF model converts but gives garbage, drifting tokens, a llama.cpp mismatch or a decode-only shape failure; or when running or resuming GGUF frontend, backend and GenAI validation batches. Not for general llama.cpp usage or unrelated build/CI failures.

2026-10-13

code-review

Review OpenVINO changes for correctness, compatibility, performance, security, testing, and maintainability. Use when reviewing a pull request or proposed diff.

2026-10-12

ov-debug

Debug OpenVINO CPU/GPU plugin inference, accuracy, performance, memory, and device compilation issues, or inspect graph transformations, using debug capabilities such as tensor dumps, execution graphs, profiling, and transformation tracing. Do NOT use for frontend model conversion failures (unsupported operators, translation errors, or source-model loading), build/configuration failures, or generic test/CI failures.

2026-10-02

Alle aus diesem Repository ansehen

ov-write-transformations

Quellinformationen

Installationsoptionen

Mit einem KI-Assistenten installieren

Quelldateien prüfen

Mehr aus diesem Repository

Mit einem KI-Assistenten installieren

Mehr aus diesem Repository