fix: simplify round 2 — deduplicate update_masks, reduce VRAM, clear cache

fix: simplify review — fix mask NMS bug, remove dead code, hoist imports

fix: add mask-level NMS in GSAM2/YSAM2 to deduplicate overlapping masks

Eliminate redundant JPEG frame loading via shared frame store

feat(ttfs): instrument segmentation time-to-first-stream

refactor: rename hf_yolov8 → yolo11 across codebase

feat(segmentation): add YSAM2 variants and mission-aware detector mapping

chore: remove dead code and unused frontend modules

refactor(gsam2): make SAM2 detector-agnostic

fix: SAM2 _prep_prompts() signature

perf: defer GPU->CPU mask transfer to render thread via LazyFrameObjects

fix: correct benchmark metrics — remove double-counting and add missing timers

perf: pipeline GSAM2 tracking + rendering with startup buffer

feat: add num_maskmem parameter to /benchmark endpoint

revert: remove torch.compile — runtime failures on HF Space

fix: drop fullgraph=True from torch.compile for broader compatibility

fix: add runtime fallback for torch.compile inductor/triton failures

fix: manual torch.compile with graceful fallback for SAM2 components

perf: enable torch.compile for SAM2 via vos_optimized flag

perf: GPU-resident tensor pipeline for SAM2 video propagation

perf: eliminate CUDA sync points in SAM2 video propagation hot-path

feat: add detailed timing metrics to GroundedSAM2 segmenter

Fix segmentation mission routing and first-frame GPT alignment

Fix cross-GPU mask device mismatch in GSAM2 reconciliation

Harden GSAM2 parallel pipeline and tracking reconciliation

Refine Grounded-SAM2 tracking behavior and video frame handling

Remove SAM3 and standardize segmentation on Grounded-SAM2

perf: Tune batch sizes and queues for A10 GPUs

Fix SAM3 batch prediction shape mismatch and add InternVL2 to frontend

feat: Integrate InternVL2 and fix SAM3 segmentation batch size issue

Implement Batch Inference & Queue Backpressure Fixes

feat(inference): enable full multi-GPU support for all models

inital commit