Skip to content

Commit fded99b

Browse files
authored
Merge branch 'main' into fix
2 parents a13cd78 + 84ad990 commit fded99b

1,567 files changed

Lines changed: 242544 additions & 41632 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎.agents/skills‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
../skills

‎.claude/settings.json‎

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,14 @@
1+
{
2+
"hooks": {
3+
"UserPromptSubmit": [
4+
{
5+
"hooks": [
6+
{
7+
"type": "command",
8+
"command": "printf '{\"hookSpecificOutput\":{\"hookEventName\":\"UserPromptSubmit\",\"additionalContext\":\"MANDATORY WORKFLOW — never skip or reorder: (1) Read the artifact first (commit, file, error, PR). (2) Identify and invoke the relevant skill via the Skill tool BEFORE forming any answer or plan — even when the answer seems obvious. (3) Only then answer using the skill context. Skipping step 2 is not allowed.\"}}'"
9+
}
10+
]
11+
}
12+
]
13+
}
14+
}

‎.claude/skills‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
../skills

‎.coderabbit.yaml‎

Lines changed: 102 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,102 @@
1+
# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2+
# SPDX-License-Identifier: Apache-2.0
3+
#
4+
# Licensed under the Apache License, Version 2.0 (the "License");
5+
# you may not use this file except in compliance with the License.
6+
# You may obtain a copy of the License at
7+
#
8+
# http://www.apache.org/licenses/LICENSE-2.0
9+
#
10+
# Unless required by applicable law or agreed to in writing, software
11+
# distributed under the License is distributed on an "AS IS" BASIS,
12+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13+
# See the License for the specific language governing permissions and
14+
# limitations under the License.
15+
16+
# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
17+
# https://docs.coderabbit.ai/getting-started/configure-coderabbit/
18+
# Validator https://docs.coderabbit.ai/configuration/yaml-validator#yaml-validator
19+
# In PR, comment "@coderabbitai configuration" to get the full config including defaults
20+
# Set the language for reviews by using the corresponding ISO language code.
21+
# Default: "en-US"
22+
language: "en-US"
23+
# Settings related to reviews.
24+
# Default: {}
25+
reviews:
26+
# Set the profile for reviews. Assertive profile yields more feedback, that may be considered nitpicky.
27+
# Options: chill, assertive
28+
# Default: "chill"
29+
profile: chill
30+
# Add this keyword in the PR/MR title to auto-generate the title.
31+
# Default: "@coderabbitai"
32+
auto_title_placeholder: '@coderabbitai title'
33+
# Auto Title Instructions - Custom instructions for auto-generating the PR/MR title.
34+
# Default: ""
35+
auto_title_instructions: 'Format: "[{modules}] {type}: {description}". Modules: model, recipe, training, data, ckpt, peft, perf, ci, doc, test, build, misc. Use comma to separate multiple modules. Type must be one of: feat, fix, refactor, chore, test. Title should be concise (<= 80 chars). Example: "[model] feat: Add Qwen3 model bridge" or "[recipe, doc] feat: Add Llama 3.1 70B recipe".'
36+
# Set the commit status to 'pending' when the review is in progress and 'success' when it is complete.
37+
# Default: true
38+
commit_status: false
39+
# Generate walkthrough in a markdown collapsible section.
40+
# Default: false
41+
collapse_walkthrough: true
42+
# Generate an assessment of how well the changes address the linked issues in the walkthrough.
43+
# Default: true
44+
assess_linked_issues: true
45+
# Include possibly related issues in the walkthrough.
46+
# Default: true
47+
related_issues: true
48+
# Related PRs - Include possibly related pull requests in the walkthrough.
49+
# Default: true
50+
related_prs: true
51+
# Suggest labels based on the changes in the pull request in the walkthrough.
52+
# Default: true
53+
suggested_labels: true
54+
# Suggest reviewers based on the changes in the pull request in the walkthrough.
55+
# Default: true
56+
suggested_reviewers: true
57+
# Generate a poem in the walkthrough comment.
58+
# Default: true
59+
poem: false
60+
# Post review details on each review. Additionally, post a review status when a review is skipped in certain cases.
61+
# Default: true
62+
review_status: false
63+
# Configuration for pre merge checks
64+
# Default: {}
65+
pre_merge_checks:
66+
# Custom Pre-merge Checks - Add unique checks to enforce your team's standards before merging a pull request. Each check must have a unique name (up to 50 characters) and clear instructions (up to 10000 characters). Use these to automatically verify coding, security, documentation, or business rules and maintain code quality.
67+
# Default: []
68+
custom_checks:
69+
- name: "Test Results for Major Changes"
70+
mode: "warning" # or "error" to block merges
71+
instructions: |
72+
If this PR contains major changes (such as new features, breaking changes, or significant refactoring), verify that the PR description includes test results or testing information.
73+
If a change could affect numerics or convergence, the PR description should include information demonstrating that there is no regression.
74+
If a change could affect performance, the PR description should include before-and-after performance numbers, as well as the configuration and context in which they apply.
75+
Pass if test results are documented or if the changes are minor.
76+
auto_review:
77+
# Configuration for auto review
78+
# Default: {}
79+
# Automatic Incremental Review - Automatic incremental code review on each push
80+
# Default: true
81+
auto_incremental_review: false
82+
# Review draft PRs/MRs.
83+
# Default: false
84+
drafts: false
85+
# Base branches (other than the default branch) to review. Accepts regex patterns. Use '.*' to match all branches.
86+
# Default: []
87+
base_branches: ["main", "r[0-9].*"]
88+
# Configuration for knowledge base
89+
# Default: {}
90+
knowledge_base:
91+
code_guidelines:
92+
# CodeRabbit will analyse and learn from your organization's code guidelines, which you can mention in the file patterns section. These guidelines will then be used to conduct thorough code reviews.
93+
# Default: {}
94+
enabled: true
95+
# Enabled - Enable CodeRabbit to enforce your organization's coding standards during reviews.
96+
# Default: true
97+
filePatterns:
98+
# File Patterns - Specify files for your coding guideline documents in this section. CodeRabbit will scan these files to understand your team's standards and apply them during code reviews. Multiple files supported. File names are case-sensitive. Common files like: (**/.cursorrules, .github/copilot-instructions.md, .github/instructions/*.instructions.md, **/CLAUDE.md, **/GEMINI.md, **/.cursor/rules/*, **/.windsurfrules, **/.clinerules/*, **/.rules/*, **/AGENT.md, **/AGENTS.md) are included by default.
99+
# Default: []
100+
- "**/skills/code-style/SKILL.md"
101+
- "**/.cursor/rules/*"
102+
- "**/CONTRIBUTING.md"

‎.dev.commit‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
cf081d5df0b34b665d214ff936f27489d7396876

‎.dockerignore‎

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -14,6 +14,5 @@ nosetests.xml
1414
coverage.xml
1515
*,cover
1616
*.log
17-
.git
1817
**/*.nemo
1918
**/*.ckpt

‎.github/CODEOWNERS‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ pyproject.toml @nvidia-nemo/automation
55
ruff.toml @nvidia-nemo/automation
66
.pre-commit-config.yaml
77

8-
scripts/performance/argument_parser.py @nvidia-nemo/automation @malay-nagda
9-
scripts/performance/setup_experiment.py @nvidia-nemo/automation @malay-nagda
10-
scripts/performance/run_script.py @nvidia-nemo/automation @malay-nagda
11-
scripts/performance/run_recipe.py @nvidia-nemo/automation @malay-nagda
8+
scripts/performance/argument_parser.py @nvidia-nemo/automation @malay-nagda @erhoo82
9+
scripts/performance/setup_experiment.py @nvidia-nemo/automation @malay-nagda @erhoo82
10+
scripts/performance/run_script.py @nvidia-nemo/automation @malay-nagda @erhoo82
11+
scripts/performance/run_recipe.py @nvidia-nemo/automation @malay-nagda @erhoo82

‎.github/ISSUE_TEMPLATE/bug_report.md‎

Lines changed: 0 additions & 28 deletions
This file was deleted.
Lines changed: 86 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,86 @@
1+
name: Bug report
2+
description: Report incorrect behavior, regressions, or broken workflows in Megatron Bridge.
3+
title: "[bug] "
4+
labels:
5+
- bug
6+
- needs-triage
7+
body:
8+
- type: markdown
9+
attributes:
10+
value: |
11+
Thanks for taking the time to file a bug report. Please keep the report focused and include the smallest repro you can share.
12+
13+
**If you already have a proposed fix, please open a PR alongside this issue.** We can discuss the solution there and help get it merged.
14+
- type: textarea
15+
id: problem
16+
attributes:
17+
label: Problem
18+
description: What is broken?
19+
placeholder: Describe the incorrect behavior, regression, or failure mode.
20+
validations:
21+
required: true
22+
- type: textarea
23+
id: minimal-repro
24+
attributes:
25+
label: Minimal repro
26+
description: Provide the smallest steps, command, or code snippet that reproduces the problem.
27+
placeholder: |
28+
1. Run ...
29+
2. Use config ...
30+
3. Observe ...
31+
render: shell
32+
validations:
33+
required: true
34+
- type: textarea
35+
id: expected-behavior
36+
attributes:
37+
label: Expected behavior
38+
description: What did you expect to happen instead?
39+
placeholder: Describe the expected output or behavior.
40+
validations:
41+
required: true
42+
- type: dropdown
43+
id: affected-area
44+
attributes:
45+
label: Affected area
46+
description: Choose the closest primary area.
47+
options:
48+
- area:model
49+
- area:recipe
50+
- area:training
51+
- area:data
52+
- area:ckpt
53+
- area:peft
54+
- area:perf
55+
- area:build
56+
- area:misc
57+
- unsure
58+
validations:
59+
required: true
60+
- type: dropdown
61+
id: regression
62+
attributes:
63+
label: Regression?
64+
description: Did this work in an earlier version, branch, or commit?
65+
options:
66+
- "Yes"
67+
- "No"
68+
- Not sure
69+
validations:
70+
required: true
71+
- type: textarea
72+
id: environment
73+
attributes:
74+
label: Environment
75+
description: Include the commit or branch, container, GPU or CPU setup, and any relevant package versions.
76+
placeholder: |
77+
Branch / commit:
78+
Container or environment:
79+
GPU / machine:
80+
Python / CUDA / PyTorch:
81+
- type: textarea
82+
id: logs
83+
attributes:
84+
label: Logs
85+
description: Paste the relevant traceback, assertion, or CI log snippet if available.
86+
render: shell

‎.github/ISSUE_TEMPLATE/feature_request.md‎

Lines changed: 0 additions & 20 deletions
This file was deleted.

0 commit comments

Comments
 (0)