GitHub · Python
aryamandarda/tamserve
Live, multi-camera object tracking with SAM3, SAM 2 and EdgeTAM, on one GPU or many. One model per GPU serves every camera: faster than the original code, about 4x less GPU memory, the same accuracy.
- Stars
- 255
- Forks
- 14
- Stars gained in 24 hours
- +163
- Forks gained in 24 hours
- +8
Topics: batching, computer-vision, edgetam, gpu, inference, model-serving, object-tracking, pytorch, sam2, segment-anything
Latest data point: Nov 20, 2026 · 255 stars · 14 forks