A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
active 2023-08-15 → 2026-08-13 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 1095 days from 2023-08-15 to 2026-08-13. Pushes: 327 total, peak 6 in a day. Pull requests: 500 total, peak 7 in a day. Issues: 212 total, peak 4 in a day. Comments: 4,045 total, peak 54 in a day. Stars: 644 total, peak 10 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 |
|---|---|---|---|---|
| dali-automaton | 1.9K | 0 | 1 | 1.9K |
| JanuszL | 964 | 108 | 171 | 448 |
| mzient | 750 | 77 | 96 | 285 |
| greptile-apps[bot] | 429 | 0 | 0 | 213 |
| jantonguirao | 280 | 31 | 46 | 107 |
| klecki | 275 | 16 | 30 | 124 |
| stiepan | 249 | 23 | 25 | 93 |
| szkarpinski | 200 | 13 | 31 | 86 |
| github-advanced-security[bot] | 177 | 0 | 0 | 121 |
| mdabek-nvidia | 170 | 10 | 10 | 69 |
| awolant | 167 | 5 | 12 | 59 |
| rostan-t | 164 | 29 | 22 | 63 |
| banasraf | 139 | 6 | 11 | 53 |
| szalpal | 122 | 5 | 12 | 41 |
| 5had3z | 67 | 0 | 11 | 35 |
| tonyreina | 54 | 0 | 3 | 31 |
| staniewzki | 36 | 3 | 9 | 15 |
| CoinCheung | 27 | 0 | 0 | 17 |
| review-notebook-app[bot] | 23 | 0 | 0 | 23 |
| jackdaw213 | 19 | 0 | 0 | 14 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#6413mzient2026-07-01 17:03Fix parallel external source forwarding recycled output buffers
- Issue comment#6404dali-automaton2026-06-24 18:47Rename TL0_self_test_Ampere to TL0_self_test_arch_next
- Pull request#6379fallintoplace2026-06-03 14:34
- Pull request#6385JanuszL2026-06-03 10:24
- Issue comment#6379dali-automaton2026-05-30 18:16Bind FileReader samples by reference
- Issue comment#6379greptile-apps[bot]2026-05-30 10:40Bind FileReader samples by reference
- Issue comment#6374greptile-apps[bot]2026-05-27 11:39Rostan t/skill onboarding
- Issue comment#6371dali-automaton2026-05-27 04:44Move to CUDA 13.3
- Issue comment#6367JanuszL2026-05-26 21:45Add support for full-range VP9 video decoding
- Issue comment#6367dali-automaton2026-05-26 11:33Add support for full-range VP9 video decoding
- Pull request#6366jantonguirao2026-05-23 17:25
- Pull request#6366jantonguirao2026-05-23 14:07
- Issue comment#6365dali-automaton2026-05-22 22:22Fix Outdated GitHub Links and Hardcoded Artifacts
- Issue comment#6363dali-automaton2026-05-22 13:15Document dynamic operator wrapper arguments
- Issue comment#6363JanuszL2026-05-22 13:13Document dynamic operator wrapper arguments
- Issue comment#6352dali-automaton2026-05-22 04:57Limit CPU video decoder codec support
- Issue comment#6362JanuszL2026-05-22 04:53Hide thread pool implementation details
- Issue comment#6357dali-automaton2026-05-21 23:49Include reader in pipelines in transparent pipelining
- Issue comment#6363JanuszL2026-05-21 22:41Document dynamic operator wrapper arguments
- Issue comment#6362JanuszL2026-05-21 22:39Hide thread pool implementation details
- Pull request#6363JanuszL2026-05-21 21:37
- Issue comment#6361fversaci2026-05-21 19:18CPU-only pipeline crashes on second feed_input due to cudaGetDevice() in AccessOrder::wait() host branch
- Issue comment#6358JanuszL2026-05-21 04:47Document that the dali-dynamic-mode skill exists
- Issue comment#6355dali-automaton2026-05-19 18:01Fix generated docs see also links
- Pull request#6344jantonguirao2026-05-12 19:21
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 644 stars here means stars gained during the window, not the repo's star count.