docs(recipes): point chat_template at where the templates actually live

[yeyu-nvidia]

What does this PR do?

Type of change: Documentation

dflash.yaml tells the reader that chat templates live in modelopt_recipes/general/speculative_decoding/chat_templates/. That directory does not exist, and this comment is its only mention anywhere in the tree:

$ git grep -n 'speculative_decoding/chat_templates'
modelopt_recipes/general/speculative_decoding/dflash.yaml:19: # Templates are in modelopt_recipes/general/speculative_decoding/chat_templates/

Templates actually sit beside each launcher example — tools/launcher/examples/Qwen/Qwen3-8B/chat_template_train.jinja, .../MiniMax/MiniMax-M2.7-DFlash/chat_template_train.jinja, and so on.

Split out of #2201, where this two-line comment was the only reason modelopt-recipes-codeowners was a required reviewer on a skills-documentation PR.

Usage

No behaviour change — comment only.

Testing

None needed; the file's only change is a YAML comment. pre-commit passes.

Before your PR is "Ready for review"

• Is this change backward compatible?: ✅
• If you copied code from any other sources or added a new PIP dependency, did you follow guidance in CONTRIBUTING.md: N/A
• Did you write any new necessary tests?: N/A
• Did you update Changelog?: N/A
• Did you get Claude approval on this PR?: N/A

🤖 Generated with Claude Code

Summary by CodeRabbit

• Documentation
  • Updated speculative decoding guidance to clarify where each model’s chat template is maintained alongside its launcher example.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 4e604f8d-f316-4031-9d54-cc613c3005b4

📥 Commits

Reviewing files that changed from the base of the PR and between b9cfdce and d82e1bd.

📒 Files selected for processing (1)

• modelopt_recipes/general/speculative_decoding/dflash.yaml

Included review availability: Your plan provides up to 12 included reviews per hour; 10 remain after this review.

---

📝 Walkthrough

Walkthrough

The DFlash speculative decoding recipe updates its chat-template documentation. The comment now shows a model-specific template path beside the launcher YAML instead of a centralized directory.

Changes

DFlash template documentation

Layer / File(s)	Summary
Document model-specific template location modelopt_recipes/general/speculative_decoding/dflash.yaml	The chat-template comment now uses an example path beside each model’s launcher YAML.

Priority: ⬇️ Low

Estimated code review effort: 1 (Trivial) | ~2 minutes

Change: Other

Merge Risk: ⚪ Minimal · up to d82e1

This documentation-only update does not change runtime behavior and is ready to merge.

🚥 Pre-merge checks | ✅ 6

✅ Passed checks (6 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly and concisely describes the documentation change. It identifies that the chat_template reference now points to the actual template locations.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0…
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Security Anti-Patterns	✅ Passed	PASS: The pull request changes only one YAML file, modelopt_recipes/general/speculative_decoding/dflash.yaml, and the diff adds/replaces documentation comments only. It introduces no Python, depende…

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Commit to this branch
• Create a new PR

---

_{Comment @coderabbitai help to get the list of available commands.}

[yeyu-nvidia]

@shengliangxu could you take a look? Two-line comment fix in a recipe YAML — it points at modelopt_recipes/general/speculative_decoding/chat_templates/, which doesn't exist. Split out of #2201 so the recipes-codeowners gate lands on this instead of on a skills-docs PR.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 78.97%. Comparing base (b9cfdce) to head (d82e1bd).
⚠️ Report is 5 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #2460      +/-   ##
==========================================
+ Coverage   71.50%   78.97%   +7.47%     
==========================================
  Files         590      590              
  Lines       64749    64748       -1     
==========================================
+ Hits        46297    51133    +4836     
+ Misses      18452    13615    -4837     

Flag	Coverage Δ
examples-diffusers	20.88% <ø> (ø)
examples-gpt-oss	13.39% <ø> (ø)
examples-hf_ptq	22.49% <ø> (-0.04%)	⬇️
examples-llm_distill	13.46% <ø> (-0.01%)	⬇️
examples-llm_eval	17.37% <ø> (ø)
examples-llm_qat	17.67% <ø> (-0.01%)	⬇️
examples-llm_sparsity	15.93% <ø> (ø)
examples-megatron_bridge	26.28% <ø> (-0.12%)	⬇️
examples-specdec_bench	13.15% <ø> (ø)
examples-speculative_decoding	17.79% <ø> (-0.07%)	⬇️
examples-torch_onnx	21.90% <ø> (ø)
examples-torch_trt	15.22% <ø> (ø)
gpu	58.36% <ø> (+25.91%)	⬆️
regression	15.15% <ø> (+0.30%)	⬆️
unit	57.85% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[shengliangxu]

LGTM

[github-actions]

PR Preview Action v1.8.1
Preview removed because the pull request was closed.
2026-09-17 23:35 UTC