TensorRT Engine for SAM-3 model by Meta AI
active 2025-11-21 → 2026-07-17 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 239 days from 2025-11-21 to 2026-07-17. Pushes: 19 total, peak 12 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 7 total, peak 1 in a day. Comments: 21 total, peak 4 in a day. Stars: 30 total, peak 2 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 |
|---|---|---|---|---|
| dataplayer12 | 37 | 19 | 2 | 12 |
| Huntersdeng | 5 | 0 | 0 | 4 |
| Copilot | 4 | 0 | 0 | 1 |
| SimonVervisch | 2 | 0 | 0 | 1 |
| wsx1q | 1 | 0 | 0 | 1 |
| aravind-trois | 1 | 0 | 0 | 1 |
| Eric123007 | 1 | 0 | 0 | 0 |
| Aravind-Sreenivas | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#18SimonVervisch2026-03-26 16:46What are these cuda errors? Because of bad compilation
- Issue comment#17SimonVervisch2026-03-19 11:34How did you measure the time of inference?
- Issue comment#7Huntersdeng2026-03-04 08:05Precision loss in TensorRT inference
- Issue#13dataplayer122026-03-02 18:20Multiple Prompts
- Issue comment#11dataplayer122026-03-02 18:19Prompt-specific input_ids baked into ONNX graph forces re-export when changing from “dog” to “cat”
- Issue comment#7wsx1q2026-02-24 03:45Precision loss in TensorRT inference
- Issue comment#14dataplayer122026-02-20 01:19SAM3 - LiteText
- Issue comment#13dataplayer122026-02-15 03:48Multiple Prompts
- Issue comment#7Huntersdeng2026-02-12 02:25Precision loss in TensorRT inference
- Issue#12Eric1230072026-01-28 09:23能提供下环境的版本吗 在自己环境下转trt失败
- Issue comment#10dataplayer122026-01-13 16:12fix: Complete memory management with dynamic optimization supportFix/memory problems
- Issue comment#7dataplayer122026-01-10 02:52Precision loss in TensorRT inference
- Issue#8dataplayer122026-01-10 02:50Illegal memory access when image shapes are odd
- Issue comment#8dataplayer122026-01-10 02:50Illegal memory access when image shapes are odd
- Pull request#9dataplayer122026-01-10 02:48
- Issue#5dataplayer122026-01-09 17:50If I want to deploy SAM3 using Triton Inference Server, how should I write the configuration file?
- Issue comment#7Huntersdeng2026-01-06 07:24Precision loss in TensorRT inference
- Issue comment#7dataplayer122026-01-06 04:34Precision loss in TensorRT inference
- Issue comment#7Huntersdeng2026-01-06 02:39Precision loss in TensorRT inference
- Issue#7Huntersdeng2026-01-05 07:27Precision loss in TensorRT inference
- Issue comment#3dataplayer122026-01-01 21:51您好，我想知道转换成trt，fps是否可以达到实时检测
- Issue#2dataplayer122026-01-01 21:48Question about compatibility with fine-tuned SAM3 models
- Issue comment#2dataplayer122026-01-01 21:48Question about compatibility with fine-tuned SAM3 models
- Pull request#4dataplayer122026-01-01 21:46
- Issue comment#1aravind-trois2026-01-01 05:51SAM3-TensorRT export potential gaps
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 30 stars here means stars gained during the window, not the repo's star count.