vLLM plugin for attention-ffn disaggregation support
C-Rank Grade: A (Welcoming) - 68/100
External PR Merge Rate: 71%
Response Time: 2h
First Timer Success: 56%
vllm-project/afd-plugin has a recorded first-timer success rate of 55.6%. Repositories ranked A typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in vllm-project/afd-plugin respond to incoming external pull requests in approximately 1.7 hours on average. Keeping PRs focused on single tasks and ensuring tests pass helps maintainers review faster.
The C-Rank™ system evaluates GitHub projects on a 0–100 scale using real data: PR merge rates, review turnaround time, active maintainer presence, and first-time contributor success. A score of 68.2 places vllm-project/afd-plugin in the A tier.
The external contributor pull request merge rate for vllm-project/afd-plugin is 71.4%, based on public PR activity from non-core contributors.
vllm-project/afd-plugin currently has 3 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
Growing Python project in vllm-project/afd-plugin welcoming community pull requests and bug fixes.
Average Response Latency
Tracks hours until a maintainer leaves a review, comment, or PR response.
External Acceptance Rate
Percentage of community pull requests successfully merged into main.
First PR Conversion
Rate at which developers submitting their first repository PR succeed.
Show contributors that your repository actively reviews and merges external pull requests.
[](https://getmerged.abhishekco.de/vllm-project/afd-plugin?utm_source=github&utm_medium=badge)
Historical health & responsiveness evolution
External PR acceptance
First PR success rate
50% receive response in
90% receive response in
Maintainer review activity heatmap & prime window prediction
Calculating local time...
Calculating local time...
Detected: UTC
Maintainers are most responsive around 12:00 UTC (12:00 UTC in your timezone). Recommended submission window is Monday - Wednesday from 10:00 to 14:00 UTC (10:00 - 14:00 UTC local).
Limited recent maintainer review activity recorded for this repository. Prediction based on heuristic baseline.
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~4 hours (89% approval). Large PRs (>500 lines) take ~8 hours (32% approval). Keep your diff compact for rapid review.
Enter your branch size and test coverage below to forecast review turnaround and get 1-click git splitting commands.
Alternative open-source projects with active maintainers in Python.
A library for PyTorch model compression and optimizations for deployment via Core AI on Apple silicon.
ResearchStudio: Our AI co-author, from research problem to final publication.
An advanced, high-performance Python client, MCP server, and REST API for reverse-engineering Perplexity AI's WebUI.
Purpose This issue is the execution-level index for active afd-plugin work. Project direction, support policy, and long-term workstreams remain in #155. Detailed design and acceptance criteria remain in the linked RFCs and issues. The linked issue or PR is the source of truth for status; this checklist is a maintainer-facing snapshot. Last reviewed: 2026-08-24 Upstream alignment GPU backend alignment with vLLM 0.26.0 — #167 NPU backend alignment with vLLM/vLLM-Ascend 0.26.0 — #168 ModelRunnerV2 GPU ModelRunnerV2 support — #223 @jiaran-king Implementation: #245 DBO support (vllm-project/vllm#50945) Ascend NPU ModelRunnerV2 support — #240 @lirx-pd Implementation: #257 DBO support #265 Native MoERunner forward refactor Refactor AFD MoE forward around native MoERunner injection — #225 Phase 1: Attention-side native MoERunner reuse Replace handwritten GPU and CAMP2p MoE forward proxies with role-specific runners that share one remote-experts implementation. R
Summary Request to initialize a repository-backed agent workflow for afd-plugin, aligned with the repository-backed agent skills workstream in #155. The goal is to make repository maintenance and review repeatable across AFD compatibility work, model adaptation, connector/distributed changes, hardware recipes, E2E validation, and releases. Current repository assets The repository already has useful sources of truth: AGENTS.md with patching, upstream-compatibility, and review requirements; CLAUDE.md, which delegates to AGENTS.md; .agents/skills/run-e2e; CPU-safe checks and hardware-gated E2E workflows. These files should remain authoritative; agent integration should orchestrate them instead of duplicating deterministic logic. Proposed initialization 1. Repository profile and adapter Register vllm-project/afd-plugin as a first-class target in InferMatrixCopilot with: a human-reviewed repository adapter and protected-branch policy; an evidence-cited profile generated from the existing
Summary AFD is an external vLLM plugin for Attention–FFN Disaggregation. The roadmap has six workstreams: compatibility, CI/CD, and release foundation; DeepSeek-V4 and GLM-5.2 model expansion; prefill workloads and chunked-prefill/prefix-cache compatibility; NVIDIA and AMD large-scale serving recipes; Kimi-K3 prefill feasibility; repository-backed agent skills. These are workstreams, not release phases. Dependencies determine when a support claim is ready, while independent work may proceed in parallel. Goals Keep AFD aligned with a deliberate, maintainable vLLM compatibility window. Make support claims precise and backed by model-, backend-, and topology-specific evidence. Provide reproducible NVIDIA and AMD large-scale serving recipes. Expand model support without silently coupling all backend lanes. Validate realistic long-prefill and agentic workloads, including chunked prefill and prefix caching. Establish basic every-PR CI and tag-triggered GitHub/PyPI releases. Provide thin
Rate what actually matters after opening a pull request here.
Rate your first-hand PR experience (review speed, maintainer responsiveness, and onboarding ease) to help other contributors.
When evaluating whether to contribute to vllm-project/afd-plugin, response velocity and maintainer engagement are crucial. GetMerged continuously tracks pull request trajectories, first-comment latency, and code review rounds to help developers avoid submitting pull requests to backlogged repositories.
Currently, maintainers of vllm-project/afd-plugin acknowledge new external contributions in approximately 1 hours. Out of all submitted pull requests from non-core authors in the last 180-day window, 71.4% were successfully merged into the primary branch.
vllm-project/afd-plugin has a recorded first-timer success rate of 55.6%. Repositories ranked Welcoming typically provide actionable feedback during code reviews and actively nurture new community contributors.
The initial maintainer response time averages ~1 hours. Keeping PRs scoped to single concerns and ensuring CI checks succeed will optimize review turnaround.
The C-Rank™ index scores repositories on a 0 to 100 scale using an objective formula: external PR merge rates, initial response speed, active maintainer count, and first-time contributor retention. A score of 68.2 places vllm-project/afd-plugin in the Welcoming tier.
The external pull request merge rate is 71.4%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, vllm-project/afd-plugin currently has 3 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.
All metrics displayed for vllm-project/afd-plugin are automatically retrieved via the public GitHub API and recalculated daily. Insider pull requests submitted by repository owners or organization members are excluded from merge rate calculations to preserve objective external contributor statistics.