-
Notifications
You must be signed in to change notification settings - Fork 212
✨ Set up comprehensive Copilot instructions with complete API design architecture and framework overview for Python 3.12 and CUDA 12 #1031
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com>
Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com>
VibhuJawa
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please follow api design for changes https://github.com/NVIDIA-NeMo/Curator/blob/main/api-design.md and look at existing modules we have like we have here: https://github.com/NVIDIA-NeMo/Curator/tree/main/nemo_curator/stages/text
|
@copilot please look at PR Review and make changes |
…terns, update API examples Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com>
Addressed all review feedback: added PyTorch to text processing libraries, removed unsupported GPU fallback patterns, updated pipeline examples to follow the API design patterns, and replaced configuration examples with actual task-centric workflow examples. (8fff4c5) |
VibhuJawa
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Minor feedback to add more stuff from our design doc
|
@copilot , please address the review about api level design |
…design.md Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com>
…rom api-design.md Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com>
Added comprehensive API design information from api-design.md including background context explaining the transition from Dask to Ray, design rationale, tradeoffs, and expanded design principles section with current state and examples references. (fa16d70) |
Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com>
VibhuJawa
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
praateekmahajan
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Signed-off-by: Vibhu Jawa <vibhujawa@gmail.com>
Co-authored-by: Sarah Yurick <53962159+sarahyurick@users.noreply.github.com> Signed-off-by: Vibhu Jawa <vibhujawa@gmail.com>
Signed-off-by: Vibhu Jawa <vibhujawa@gmail.com>
Fixed all markdown linting issues in the copilot instructions file. Addressed MD022 (headings spacing), MD032 (lists spacing), MD031 (code blocks spacing), and MD040 (code language specification) violations. The file now passes markdownlint validation with the repository's configuration. (aad5c86) |
|
/ok to test 1ef6dd1 |
…architecture and framework overview for Python 3.12 and CUDA 12 (#1031) * Initial plan * Add comprehensive GitHub Copilot instructions for NVIDIA NeMo Curator Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Enhance Copilot instructions with explicit Python 3.12 and CUDA 12 focus Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Address review feedback: add PyTorch, remove unsupported fallback patterns, update API examples Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Add comprehensive API design principles and core components from api-design.md Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Expand API design section with comprehensive background and context from api-design.md Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Remove Dask references and background sections per review feedback Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Update task-centric architecture description to mention Ray Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Add comprehensive framework overview with key components, execution flow, and development guidelines Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Addressing PR comments Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Update .github/copilot-instructions.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Signed-off-by: Vibhu Jawa <vibhujawa@gmail.com> --------- Signed-off-by: Vibhu Jawa <vibhujawa@gmail.com> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> Co-authored-by: Vibhu Jawa <vjawa@nvidia.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Signed-off-by: NeMo Bot <nemo-bot@nvidia.com>
…architecture and framework overview for Python 3.12 and CUDA 12 (#1031) (#1035) * Initial plan * Add comprehensive GitHub Copilot instructions for NVIDIA NeMo Curator * Enhance Copilot instructions with explicit Python 3.12 and CUDA 12 focus * Address review feedback: add PyTorch, remove unsupported fallback patterns, update API examples * Add comprehensive API design principles and core components from api-design.md * Expand API design section with comprehensive background and context from api-design.md * Remove Dask references and background sections per review feedback * Update task-centric architecture description to mention Ray * Add comprehensive framework overview with key components, execution flow, and development guidelines * Addressing PR comments * Update .github/copilot-instructions.md --------- Signed-off-by: Vibhu Jawa <vibhujawa@gmail.com> Signed-off-by: NeMo Bot <nemo-bot@nvidia.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> Co-authored-by: Vibhu Jawa <vjawa@nvidia.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
…architecture and framework overview for Python 3.12 and CUDA 12 (NVIDIA-NeMo#1031) * Initial plan * Add comprehensive GitHub Copilot instructions for NVIDIA NeMo Curator Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Enhance Copilot instructions with explicit Python 3.12 and CUDA 12 focus Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Address review feedback: add PyTorch, remove unsupported fallback patterns, update API examples Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Add comprehensive API design principles and core components from api-design.md Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Expand API design section with comprehensive background and context from api-design.md Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Remove Dask references and background sections per review feedback Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Update task-centric architecture description to mention Ray Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Add comprehensive framework overview with key components, execution flow, and development guidelines Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Addressing PR comments Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> * Update .github/copilot-instructions.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Signed-off-by: Vibhu Jawa <vibhujawa@gmail.com> --------- Signed-off-by: Vibhu Jawa <vibhujawa@gmail.com> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: VibhuJawa <4837571+VibhuJawa@users.noreply.github.com> Co-authored-by: Vibhu Jawa <vjawa@nvidia.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This PR implements comprehensive GitHub Copilot instructions for the NVIDIA NeMo Curator repository, incorporating the complete API design architecture, framework overview, and task-centric patterns for Python 3.12 with optional CUDA 12 GPU environments.
Key Features
Complete API Design Architecture:
XtoYtransformations where both can beTask | list[Task] | NoneTask,ProcessingStage,Pipeline, andBaseExecutorwith proper Generic typingFramework Overview:
Development Environment Setup:
uvpackage manager workflow with dependency groups and virtual environment managementCode Quality and Documentation:
Recent Updates:
The instructions provide GitHub Copilot with comprehensive context about the repository's task-based architecture and multi-backend framework capabilities, enabling better code suggestions that align with the fault-tolerant, resource-aware design patterns required for heterogeneous computing environments.
Fixes #981.
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.