Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
C-Rank Grade: A (Welcoming) - 68/100
External PR Merge Rate: 72%
Response Time: 3h
First Timer Success: 88%
sqliteai/warp has a recorded first-timer success rate of 87.5%. Repositories ranked A typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in sqliteai/warp respond to incoming external pull requests in approximately 3.1 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 68.5 places sqliteai/warp in the A tier.
The external contributor pull request merge rate for sqliteai/warp is 71.9%, based on public PR activity from non-core contributors.
sqliteai/warp currently has 2 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
Active maintainer team in sqliteai/warp 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/sqliteai/warp?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 20:00 UTC (20:00 UTC in your timezone). Recommended submission window is Wednesday - Friday from 17:00 to 21:00 UTC (17:00 - 21:00 UTC local).
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~4 hours (90% approval). Large PRs (>500 lines) take ~15 hours (32% approval). Keep your diff compact for rapid review.
We have a 128-GB Ryzen AI Max+ 395 Strix Halo Linux system with Zen 5 AVX-512/VBMI. We can run the open Gate-7 fine cache sweep at 200+ tokens and characterize the larger-memory side of the paging cliff. Is Gate 7 already being worked, and would a Strix Halo dataset be useful? If yes, what exact command/configuration/output format would you prefer? For reference, the gate as we understand it: docs/GATES.md @ 2056d44 (lines 318–375) — tests/sweep.c with cache=, a fine grid between 287 and 1498 slots, over a long generation (200 tokens or more), one process, interleaved arms per LEARNED.md §38. Kill criterion: if at 200+ tokens a 3–4 GB cache is no longer within ~10% of floor + 1x, the rule stands as written.
WASTE_ENABLE_CUDA=1 has been a reachable Makefile flag since the skeleton, and there is still no src/cuda.cu behind it — the build stops with a message saying so, which is the honest state but not a decision. This issue is to record what the decision would have to rest on, because "write the kernels" is not the work. Why this is not a backend Metal is the one accelerator that got written, and it is off by default because it was measured slower: total CPU/NEON 15.93 s Metal 19.43 s 22% slower lm_head is the clearest case, one dispatch per token over 1.17 GB of int8 weights: CPU 6 ms against GPU 22 ms — 195 GB/s against 53 GB/s. The CPU path was already running at the machine's memory bandwidth on a bandwidth-bound matvec, so there was no headroom to take, and the GPU paid a synchronous round-trip per call on top. The conclusion in docs/BACKENDS.md is about shape rather than about Metal, and it applies unchanged to CUDA: This engine issues several hundred small dep
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 sqliteai/warp, 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 sqliteai/warp acknowledge new external contributions in approximately 3 hours. Out of all submitted pull requests from non-core authors in the last 180-day window, 71.9% were successfully merged into the primary branch.
sqliteai/warp has a recorded first-timer success rate of 87.5%. Repositories ranked Welcoming typically provide actionable feedback during code reviews and actively nurture new community contributors.
The initial maintainer response time averages ~3 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 68.5 places sqliteai/warp in the Welcoming tier.
The external pull request merge rate is 71.9%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, sqliteai/warp 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 sqliteai/warp 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.