Skip to content

Conversation

Copy link
Contributor

Copilot AI commented Aug 15, 2025

This PR adds a comprehensive .github/copilot-instructions.md file that provides detailed development guidance for GitHub Copilot coding agents working on the tritonBLAS repository.

Key Features

Validated Build Process & Timing:

  • Docker setup instructions with accurate timing (7-10 minutes build time)
  • Dependency fetching process documentation (~4 seconds total)
  • pip installation guidance with proper timeout recommendations (2-5 minutes)
  • All commands tested and validated for accuracy

Critical Environment Requirements:

  • Clear documentation that ROCm/CUDA GPU environments are required
  • Warning that CPU-only environments will fail during triton installation
  • Docker recommended as the primary development approach due to complex dependencies

Complete Development Workflow:

  • Step-by-step setup instructions with proper timing expectations
  • Code quality integration (ruff linting and formatting commands)
  • Testing requirements and GPU dependencies
  • API usage examples for both performance and drop-in replacement APIs
  • Project structure navigation guide with key directories and files

Comprehensive Troubleshooting:

  • Common build issues and their solutions
  • Network timeout handling
  • Disk space management for Docker builds
  • Environment-specific error resolution

Explicit Timing and Safety Warnings:

  • "NEVER CANCEL" warnings for long-running operations
  • Specific timeout recommendations (15+ minutes for Docker, 10+ minutes for pip)
  • Accurate timing measurements for all development operations

The instructions start with a firm directive to always follow the provided guidance first before searching for additional context, as requested in the issue requirements. All commands and timing information were extensively validated through testing to ensure accuracy and reliability.

Fixes #11.


💡 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.

…s and timing

Co-authored-by: neoblizz <9790745+neoblizz@users.noreply.github.com>
Copilot AI changed the title [WIP] ✨ Set up Copilot instructions Add comprehensive GitHub Copilot instructions for tritonBLAS development Aug 15, 2025
Copilot AI requested a review from neoblizz August 15, 2025 20:08
@neoblizz neoblizz marked this pull request as ready for review September 10, 2025 07:05
Copilot AI review requested due to automatic review settings September 10, 2025 07:05

This comment was marked as outdated.

neoblizz and others added 2 commits September 10, 2025 00:08
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This PR adds comprehensive GitHub Copilot instructions for tritonBLAS development, providing detailed guidance for coding agents working on the repository. The instructions emphasize the critical requirement for ROCm/CUDA GPU environments and provide validated build processes with accurate timing information.

Key changes:

  • Complete development workflow documentation with Docker setup (recommended) and local installation options
  • Validated build timing and safety warnings for long-running operations
  • Comprehensive troubleshooting guide for common issues and environment-specific errors

Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

✨ Set up Copilot instructions

2 participants