feat(doc): update docker tag examples by NanoCode012 · Pull Request #2851 · axolotl-ai-cloud/axolotl

NanoCode012 · 2025-07-01T05:18:50Z

Description

We encouraged users to use cu128 for Blackwell but didn't provide example tags. This PR adds that.

Motivation and Context

How has this been tested?

Screenshots (if appropriate)

Types of changes

Social Handles (Optional)

Summary by CodeRabbit

Documentation
- Updated Docker documentation to include new and alternative image tags for base and main images.
- Revised tagged release version information to reflect the latest release.

coderabbitai · 2025-07-01T05:18:56Z

"""

Walkthrough

The documentation for Docker image tags was updated to include new and alternative tags for both base and main images, reflecting the availability of updated versions. The tagged release version reference was also changed from 0.9.2 to 0.10.1.

Changes

File(s)	Change Summary
docs/docker.qmd	Updated Docker image tags for base and main images; revised tagged release version from 0.9.2 to 0.10.1.

Possibly related PRs

feat(modal): update docker tag to use torch2.6 from torch2.5 #2749: Updates the default Docker image tag string in code to use a newer PyTorch version, similar to this PR's documentation update for Docker tags.
feat(doc): clarify minimum pytorch and cuda to use blackwell #2704: Adds clarifying notes about minimum PyTorch and CUDA versions for Blackwell GPUs, related to the documentation of Docker image compatibility.

Suggested labels

documentation

Suggested reviewers

SalmanMohammadi
winglian

Poem

🐇
Docker tags hop, a version parade,
New numbers gleam where old once stayed.
Images fresh as morning dew,
Docs now show what's latest and true.
Rabbits rejoice in this tidy array—
Pull the right tag, and code away!

"""

📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 3f6c3a7 and 7d2d969.

📒 Files selected for processing (1)

docs/docker.qmd (3 hunks)

🚧 Files skipped from review as they are similar to previous changes (1)

docs/docker.qmd

⏰ Context from checks skipped due to timeout of 90000ms (1)

GitHub Check: preview

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

Review comments: Directly reply to a review comment made by CodeRabbit. Example:
- I pushed a fix in commit <commit_id>, please review it.
- Explain this complex logic.
- Open a follow-up GitHub issue for this discussion.
Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
- @coderabbitai explain this code block.
- @coderabbitai modularize this function.
PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
- @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
- @coderabbitai read src/utils.ts and explain its main purpose.
- @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
- @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

@coderabbitai pause to pause the reviews on a PR.
@coderabbitai resume to resume the paused reviews.
@coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
@coderabbitai full review to do a full review from scratch and review all the files again.
@coderabbitai summary to regenerate the summary of the PR.
@coderabbitai generate docstrings to generate docstrings for this PR.
@coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
@coderabbitai resolve resolve all the CodeRabbit review comments.
@coderabbitai configuration to show the current CodeRabbit configuration for the repository.
@coderabbitai help to get help.

Other keywords and placeholders

Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (`.coderabbit.yaml`)

You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
Please see the configuration documentation for more information.
If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

Visit our Documentation for detailed information on how to use CodeRabbit.
Join our Discord Community to get help, request features, and share feedback.
Follow us on X/Twitter for updates and announcements.

coderabbitai

Actionable comments posted: 0

🧹 Nitpick comments (3)

docs/docker.qmd (3)
11-13: Capitalize “PyTorch” for brand correctness

Minor nit: “PyTorch” is the canonical spelling (capital “T”).
-For Blackwell GPUs, please use the tags with Pytorch 2.7.1 and CUDA 12.8.
+For Blackwell GPUs, please use the tags with PyTorch 2.7.1 and CUDA 12.8.
33-38: Keep base-image tag examples ordered & scoped

Nice addition of the cu128 example.
To reduce visual scanning cost, consider ordering the list by CUDA version (desc) and, within that, by PyTorch version. This keeps the Blackwell-focused tag (cu128-2.7.1) clearly on top and prevents the older cu126-2.6.0 from appearing between two 2.7.1 examples.

75-79: Apply the same ordering to “main” image tags

Same comment as above: ordering the main-* examples by CUDA version first (cu128 ➜ cu126 ➜ cu124) and then by PyTorch version makes it easier for readers to spot the recommended tag quickly.

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 35fdbce and 3f6c3a7.

📒 Files selected for processing (1)

docs/docker.qmd (2 hunks)

⏰ Context from checks skipped due to timeout of 90000ms (1)

GitHub Check: preview

🔇 Additional comments (1)

docs/docker.qmd (1)

85-85: Confirm version bump consistency across docs

The tagged release example now shows 0.10.1. Please verify that all other documentation sections (e.g., CHANGELOG, README badges) and any automation referring to the previous 0.9.2 tag are updated accordingly.

NanoCode012 · 2025-07-01T05:22:41Z

@coderabbitai , can you check where the ordering needs to be? I think it's already ordered across sections by cuda then torch.

coderabbitai · 2025-07-01T05:23:39Z

Tip

For best results, initiate chat on the files or code changes.

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
# Read the docker.qmd file to examine the Docker tag ordering
cat docs/docker.qmd

Length of output: 3393

@NanoCode012, you're absolutely correct! After examining the docs/docker.qmd file, I can confirm that the Docker tags are already properly ordered across both sections:

Current ordering pattern:

Primary sort: CUDA version (descending: cu128 → cu126 → cu124)
Secondary sort: PyTorch version (descending within same CUDA: 2.7.1 → 2.6.0 → 2.5.1)

Base image tags:

main-base-py3.11-cu128-2.7.1 (newest CUDA + newest PyTorch)
main-base-py3.11-cu126-2.7.1
main-base-py3.11-cu126-2.6.0
main-base-py3.11-cu124-2.6.0
main-base-py3.11-cu124-2.5.1

Main image tags:

main-py3.11-cu128-2.7.1
main-py3.11-cu126-2.7.1
main-py3.11-cu126-2.6.0
main-py3.11-cu124-2.6.0
main-py3.11-cu124-2.5.1

This ordering is logical and user-friendly, as it prioritizes the newest CUDA versions first (important for Blackwell GPU compatibility), followed by the newest PyTorch versions within each CUDA group. No reordering is needed! 👍

github-actions · 2025-07-01T05:24:12Z

🚀 Deployed on https://686371c4df09fcdf921100ed--resonant-treacle-0fd729.netlify.app

feat(doc): update docker tag examples

3f6c3a7

coderabbitai Bot reviewed Jul 1, 2025

View reviewed changes

chore: comment

7d2d969

github-actions Bot temporarily deployed to preview July 1, 2025 05:27 Inactive

salmanmohammadi approved these changes Jul 1, 2025

View reviewed changes

winglian added the ready to merge label Jul 1, 2025

winglian merged commit bf5928d into main Jul 2, 2025
3 checks passed

winglian deleted the feat/doc-128 branch July 2, 2025 12:05

This was referenced Jul 8, 2025

release v0.11.0 #2875

Merged

feat(doc): re-add docker 2.7.0 tag back #2902

Merged

coderabbitai Bot mentioned this pull request May 3, 2026

feat: add Blackwell-targeted base Dockerfile (fixes #3630) #3640

Closed

4 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

feat(doc): update docker tag examples#2851

feat(doc): update docker tag examples#2851
winglian merged 2 commits into
mainfrom
feat/doc-128

NanoCode012 commented Jul 1, 2025 •

edited by coderabbitai Bot

Loading

Uh oh!

coderabbitai Bot commented Jul 1, 2025 •

edited

Loading

Chat

Support

CodeRabbit Commands (Invoked using PR comments)

Other keywords and placeholders

CodeRabbit Configuration File (`.coderabbit.yaml`)

Documentation and Community

Uh oh!

coderabbitai Bot left a comment

Uh oh!

NanoCode012 commented Jul 1, 2025

Uh oh!

coderabbitai Bot commented Jul 1, 2025

Uh oh!

github-actions Bot commented Jul 1, 2025 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Uh oh!

Conversation

NanoCode012 commented Jul 1, 2025 • edited by coderabbitai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Motivation and Context

How has this been tested?

Screenshots (if appropriate)

Types of changes

Social Handles (Optional)

Summary by CodeRabbit

Uh oh!

coderabbitai Bot commented Jul 1, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Possibly related PRs

Suggested labels

Suggested reviewers

Poem

Chat

Support

CodeRabbit Commands (Invoked using PR comments)

Other keywords and placeholders

CodeRabbit Configuration File (.coderabbit.yaml)

Documentation and Community

Uh oh!

coderabbitai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

NanoCode012 commented Jul 1, 2025

Uh oh!

coderabbitai Bot commented Jul 1, 2025

Uh oh!

github-actions Bot commented Jul 1, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

NanoCode012 commented Jul 1, 2025 •

edited by coderabbitai Bot

Loading

coderabbitai Bot commented Jul 1, 2025 •

edited

Loading

CodeRabbit Configuration File (`.coderabbit.yaml`)

github-actions Bot commented Jul 1, 2025 •

edited

Loading