Skip to content

Improve model integration skills from merged PRs - #482

Merged
justinchuby merged 2 commits into
mainfrom
justinchuby-add-three-hf-models
Aug 14, 2026
Merged

Improve model integration skills from merged PRs#482
justinchuby merged 2 commits into
mainfrom
justinchuby-add-three-hf-models

Conversation

@justinchuby

Copy link
Copy Markdown
Member

Summary

  • distill post-single-shot lessons from the Parakeet CTC, Mage-VL, Nemotron Parse, LFM2.5, Moonshine, MiniCPM-V, Qwen Image Edit, and Muse Glimmer integrations
  • tighten source/config/revision fidelity, real processor and runtime contracts, semantic multi-dtype validation, exact golden testing, and weighted graph optimization evidence
  • add precise CI baseline triage, targeted GPU validation, linear rebase/worktree guidance, quantization schema checks, and executable diffusion pipeline requirements
  • shorten the duplicated multimodal float32 input section and resolve contradictory encoder/component import guidance

Sources

Direct agent retrospectives plus commit/review history for merged PRs #462-#465, #471-#473, and #475.

Validation

  • documentation diff is whitespace-clean
  • initialized repository-pinned Ruff/lintrunner tooling
  • independent rubber-duck review found no blocking issues; follow-up consistency suggestions were applied

No runtime code is changed.

Capture recurring lessons from agent retrospectives and review history across recent model integrations. Tighten source/config fidelity, processor and runtime contracts, real GPU validation, graph optimization evidence, CI triage, and multi-agent rebase guidance while shortening duplicated multimodal dtype documentation.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Signed-off-by: Justin Chu <justinchu@microsoft.com>
@justinchuby
justinchuby requested review from a team and a lite review from Copilot August 14, 2026 00:34
@github-actions

github-actions Bot commented Aug 14, 2026

Copy link
Copy Markdown

Performance Comparison

Comparing b10825499cd247

Model Metric Baseline Current Delta
bert (feature-extraction) model_size_bytes 359 KB 359 KB +0.0%
bert (feature-extraction) num_nodes 60 60 +0.0%
falcon model_size_bytes 364 KB 364 KB +0.0%
falcon num_nodes 66 66 +0.0%
gemma2 model_size_bytes 428 KB 428 KB +0.0%
gemma2 num_nodes 105 105 +0.0%
gpt2 model_size_bytes 388 KB 388 KB +0.0%
gpt2 num_nodes 54 54 +0.0%
llama model_size_bytes 425 KB 425 KB +0.0%
llama num_nodes 60 60 +0.0%
llama (static-cache) model_size_bytes 425 KB 425 KB +0.0%
llama (static-cache) num_nodes 56 56 +0.0%
mamba (ssm-text-generation) model_size_bytes 296 KB 296 KB +0.0%
mamba (ssm-text-generation) num_nodes 94 94 +0.0%
phi3 model_size_bytes 421 KB 421 KB +0.0%
phi3 num_nodes 58 58 +0.0%
phi3 (static-cache) model_size_bytes 421 KB 421 KB +0.0%
phi3 (static-cache) num_nodes 54 54 +0.0%
qwen2 model_size_bytes 425 KB 425 KB +0.0%
qwen2 num_nodes 60 60 +0.0%
qwen2 (static-cache) model_size_bytes 425 KB 425 KB +0.0%
qwen2 (static-cache) num_nodes 56 56 +0.0%
qwen3_5_moe (hybrid-text-generation) model_size_bytes 506 KB 506 KB +0.0%
qwen3_5_moe (hybrid-text-generation) num_nodes 264 264 +0.0%
qwen3_5_text (hybrid-text-generation) model_size_bytes 458 KB 458 KB +0.0%
qwen3_5_text (hybrid-text-generation) num_nodes 126 126 +0.0%
qwen3_5_vl (hybrid-qwen-vl) model_size_bytes 977 KB 977 KB +0.0%
qwen3_5_vl (hybrid-qwen-vl) num_nodes 428 428 +0.0%
t5 (seq2seq) model_size_bytes 836 KB 836 KB +0.0%
t5 (seq2seq) num_nodes 166 166 +0.0%
whisper (speech-to-text) model_size_bytes 1008 KB 1008 KB +0.0%
whisper (speech-to-text) num_nodes 128 128 +0.0%

No performance regressions.

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

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 updates the internal “skills” documentation under .agents/skills/ to capture integration lessons learned from recently merged model PRs, with an emphasis on tighter runtime/processor contracts, reproducible golden testing, and evidence-based CI/runtime validation practices.

Changes:

  • Strengthen testing guidance around end-to-end ONNX stage wiring, exact/reproducible goldens, and cache/processor contract validation.
  • Clarify component import patterns, canonical ONNX op preferences, and public-call compatibility expectations.
  • Add sharper CI triage, runtime support verification, quantization caveats, and diffusion pipeline executability requirements.

Reviewed changes

Copilot reviewed 10 out of 10 changed files in this pull request and generated 1 comment.

Show a summary per file
File Description
.agents/skills/writing-tests/SKILL.md Expands integration/golden test guidance (wiring, masks/defaults, processor contracts, reproducibility).
.agents/skills/reusable-components/SKILL.md Clarifies intra-components import guidance and adds operator/compatibility best practices.
.agents/skills/quality-checklist/SKILL.md Tightens definition-of-done checks (pinned revision propagation, dtype semantics, CI tool verification, CI triage).
.agents/skills/ort-genai-config/SKILL.md Adds guidance for hybrid cache slot derivation and CUDA Graph capture scope/validation.
.agents/skills/onnx-export-quantization/SKILL.md Notes Attention rewrite/schema mismatch pitfalls and validation expectations.
.agents/skills/multimodal-models/SKILL.md Reframes processor-to-graph contract guidance; emphasizes real processor batches and mixed-media edge cases.
.agents/skills/multi-agent-coordination/SKILL.md Refines multi-agent workflow guidance and branch strategy/CI triage recommendations.
.agents/skills/diffusion-models/SKILL.md Adds an explicit “prove pipeline executability” requirement for diffusion exports/runtime claims.
.agents/skills/debugging-multimodal/SKILL.md Updates encoder input dtype guidance to align with real processor float32 boundaries.
.agents/skills/adding-a-new-model/SKILL.md Reinforces revision pinning, config-semantic fidelity, and compatibility traps checklist items.

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

Comment thread .agents/skills/diffusion-models/SKILL.md Outdated
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Signed-off-by: Justin Chu <justinchuby@users.noreply.github.com>
@justinchuby
justinchuby merged commit 9b07f09 into main Aug 14, 2026
14 of 22 checks passed
@justinchuby
justinchuby deleted the justinchuby-add-three-hf-models branch August 14, 2026 00:50
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.

2 participants