A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包
C-Rank Grade: A (Welcoming) - 64/100
External PR Merge Rate: 68%
Response Time: -
First Timer Success: 62%
intel/auto-round has a recorded first-timer success rate of 61.9%. Repositories ranked A typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in intel/auto-round respond to incoming external pull requests in approximately 0.0 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 63.8 places intel/auto-round in the A tier.
The external contributor pull request merge rate for intel/auto-round is 68.4%, based on public PR activity from non-core contributors.
intel/auto-round currently has 2 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
Highly welcoming maintainers in intel/auto-round. Prompt code reviews with positive guidance for new contributors.
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/intel/auto-round?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 05:00 UTC (05:00 UTC in your timezone). Recommended submission window is Wednesday - Friday from 02:00 to 06:00 UTC (02:00 - 06:00 UTC local).
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~16 hours (86% approval). Large PRs (>500 lines) take ~115 hours (31% approval). Keep your diff compact for rapid review.
Feature Description 通过检查目标文件夹，确认文件是否属于当前正在执行的命令 需要cache 执行参数，方便resume检查。 需要cache 标记： 待处理的文件，已经处理的文件。 检查通过，则跳过已经处理过的文件 Motivation and Use Case 如果网断了，或者磁盘满了， 下次启动期望继续 Alternatives Considered No response Definition of Done No response Additional Context No response
When loading a model across multiple devices using device_map="auto", the accelerate library attaches hooks to move module inputs to the correct devices automatically. For certain models (for example, gpt‑oss), we replace the original MoE modules during initialization. However, after this replacement, the newly inserted modules do not have the required Accelerate hooks attached. As a result, input tensors may not be dispatched to the correct devices. We need to investigate when Accelerate binds these hooks during the model loading process. Based on that, we should re-dispatch (or re-attach hooks to) the replaced modules if necessary to ensure correct multi-device execution. If needed, we can dispatch the replaced model with dispatch_model: from accelerate.big_modeling import dispatch_model
For Deepseek v32 and similar FP8 models, it is preferable to keep layers specified in ignore_layers (such as indexer or attn) in their original FP8 format, rather than dequantizing them to BF16. Expected behavior: AR_LOG_LEVEL=TRACE auto_round --model /models/Qwen3-8B-FP8 --ignore_layers "attn" All layers within attention (matching "attn") should remain in FP8 format, not be dequantized to BF16 or float. Depends on #1283 cc @wenhuach21 @thuang6 @xin3he
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 intel/auto-round, 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 intel/auto-round acknowledge new external contributions in approximately -. Out of all submitted pull requests from non-core authors in the last 180-day window, 68.4% were successfully merged into the primary branch.
intel/auto-round has a recorded first-timer success rate of 61.9%. Repositories ranked Welcoming typically provide actionable feedback during code reviews and actively nurture new community contributors.
The initial maintainer response time averages ~-. 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 63.8 places intel/auto-round in the Welcoming tier.
The external pull request merge rate is 68.4%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, intel/auto-round currently has 2 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.
All metrics displayed for intel/auto-round 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.