Repository Issue Activity (beta)

#408 Streaming Version of SAM3

#604 SAM3 mask exemplars: claimed in the paper, unusable in the release

#252 Missing modules after installation

#420 Request to Hugging Face Repo Rejected

#590 Constant "We're at capacity right now" error on Meta AI Demos playground

#517 SAM3.1 - Suggestion installation guide 3.1

#609 SAM3 → ONNX → Triton Inference Server: full image-model deployment (text, box + cross-crop exemplars, interactive PVS)

#612 SAM3.1 Tracker Propagation Failure

#611 Question about reproducing semantic‑segmentation mIoU in SAM‑3

#521 Sam 3.1 Transformers library support

#610 Full fine-tuning fails because ViT `Mlp.forward()` calls inference-only `addmm_act`

#224 Request for Official ONNX Export + TensorRT Conversion Scripts for SAM3

#391 Can SAM3 be deployed using Triton Inference Server? How should the configuration file be written?

#206 How to use text prompts to track multiple categories in one video?

#440 Loss is nan

#606 `build_sam3_image_model(checkpoint_path=...)` can silently load nothing for fine-tuned checkpoints

#595 How were the choices of memory_temporal_stride_for_eval=1 and num_maskmem=7 made?

#317 Transfer concept from one image to another

#507 RuntimeError: mat1 and mat2 must have the same dtype, but got BFloat16 and Float during image inference

#597 How I can run this on mac No module named 'triton'

#163 How to fine-tune on my own image/video datasets?

#594 In the same scenario, most of the reasoning can be correct, while a small portion yields no result.

#596 Is CUDA 12.8 a hard requirement, or just the dev environment default?

#495 Tracking long videos

#577 ValueError when running sam3_image_interactive.ipynb