The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.
active 2025-01-29 → 2026-06-25 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 513 days from 2025-01-29 to 2026-06-25. Pushes: 123 total, peak 6 in a day. Pull requests: 48 total, peak 3 in a day. Issues: 25 total, peak 2 in a day. Comments: 177 total, peak 14 in a day. Stars: 124 total, peak 4 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| morgolock | 173 | 53 | 13 | 59 |
| gunes-arm | 124 | 22 | 15 | 56 |
| ArmDude | 44 | 20 | 6 | 11 |
| andflo-Arm | 18 | 10 | 5 | 3 |
| developer-compute | 11 | 11 | 0 | 0 |
| wajahat-abbas | 10 | 2 | 0 | 5 |
| alvoron | 8 | 0 | 0 | 5 |
| walidbr | 8 | 2 | 3 | 2 |
| aestriplex | 7 | 0 | 1 | 3 |
| Martinfx | 7 | 0 | 1 | 5 |
| Dongsung-arm | 7 | 0 | 0 | 1 |
| Sqvid | 5 | 0 | 1 | 3 |
| hpc-qti | 4 | 0 | 0 | 3 |
| DavidMansell | 4 | 1 | 2 | 1 |
| fadara01 | 3 | 0 | 0 | 2 |
| aobolensk | 3 | 0 | 0 | 1 |
| mcfi | 3 | 0 | 0 | 3 |
| mgxhhg | 2 | 0 | 0 | 1 |
| Copilot | 2 | 0 | 0 | 2 |
| allnes | 2 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Pull request#1283DavidMansell2026-04-24 12:21
- Issue comment#1273morgolock2026-04-20 09:01NEPoolingLayer - int8 vs fp16 performance
- Pull request#1270morgolock2026-04-02 10:04
- Issue comment#1186morgolock2026-04-02 07:04Sparse tensor data structures
- Issue comment#1223gunes-arm2026-03-11 11:03feat: Add experimental support for FreeBSD(R) OS
- Issue comment#1265morgolock2026-03-04 11:49Lack of epsilon aware comparison in NETopKV for Fp32 data type
- Pull request#1265morgolock2026-03-04 11:17
- Issue comment#1255knowledgaction2026-03-01 23:47How to Dynamically Update Input for an MLP Inference Pipeline Using ACL
- Pull request#1263ArmDude2026-02-27 15:28
- Issue comment#1223Martinfx2026-02-26 19:48feat: Add experimental support for FreeBSD(R) OS
- Issue comment#1223gunes-arm2026-02-26 15:56feat: Add experimental support for FreeBSD(R) OS
- Pull request#1257gunes-arm2026-02-26 14:32
- Issue comment#1261gunes-arm2026-02-25 15:10feat: Add validation of indices to MaxUnpooling kernel
- Pull request#1259walidbr2026-02-25 14:41
- Pull request#1261jenselofsson2026-02-25 14:23
- Pull request#1260ArmDude2026-02-25 10:59
- Pull request#1259walidbr2026-02-19 15:31
- Pull request#1259walidbr2026-02-19 15:31
- Issue comment#1220hpc-qti2026-02-13 05:23SME1 kernel support for AI workloads using ArmNN
- Issue comment#1254alvoron2026-02-09 10:56Android aarch64 SCons build uses `llvm-as` without target flags
- Pull request#1256morgolock2026-02-05 10:59
- Issue comment#1252alvoron2026-01-28 12:18Shared TensorInfo flips `is_resizable` and makes `extend_padding` throw
- Issue#1252alvoron2026-01-27 09:48Shared TensorInfo flips `is_resizable` and makes `extend_padding` throw
- Issue#1236aobolensk2026-01-22 14:19Tensor size limits are too strict for Gemm
- Issue comment#1227morgolock2026-01-19 18:09NEON implementation for TopK/TopKV
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 124 stars here means stars gained during the window, not the repo's star count.