Improvements to Triton fast path for RF-DETR Instance Segmentation - #2443

Replace the per-frame PIL-bilinear-antialias + to_tensor + normalize chain
in the RF-DETR TRT instance-segmentation model with a single Triton
kernel that resizes, swaps BGR↔RGB, scales by 1/255, and applies
ImageNet normalization — writing straight into the preallocated TRT
input buffer.

Byte-exact port of PIL's separable bilinear-antialias resize
(PRECISION_BITS=22, int32 fixed-point, uint8 quantization between the
horizontal and vertical passes). The horizontal uint8 intermediate
lives in registers.

Correctness
- Preproc max abs error vs PIL: 4.77e-7 (fp32 ULP on the final
  /255+normalize step; the uint8 resize result is byte-identical).
- Full coco/val2017 detection parity (rfdetr-seg-nano, conf=0.4):
  26,721 / 26,721 matched at IoU>0.5, mean box IoU 1.0000,
  |Δscore| 0, 0 class-id disagreements, all matched masks
  pixel-identical.

Performance (vehicles_312px.mp4, 538 frames)
- Baseline (PIL path): 76.25 fps
- Triton fast path:    99.83 fps (+31%)
- Preproc microbench (1080p → 312²): 27.0 ms → 2.8 ms per frame (~10×)

Scope
- Gated on: single-image numpy uint8 HWC input, stretch/letterbox/
  center-crop/letterbox-reflect resize modes (all collapse to a single
  PIL stretch when dataset_version_resize_dimensions is None, verified
  via synthetic-package test), no static_crop/grayscale/contrast,
  3-channel, scaling_factor in {None, 255}, normalization set.
- Falls back to the existing PIL-based pre_process_network_input
  when any precondition fails.

Also adds the benchmark driver
development/stream_interface/rfdetr_nano_seg_trt_workflow.py used to
measure the above numbers.

INFERENCE_MODELS_RFDETR_TRITON_PREPROC_ENABLED (default true). Setting
it to false short-circuits _try_fast_preprocess so every call falls
back to the PIL reference path — useful for A/B benchmarking and as an
escape hatch if the fused kernel is ever implicated in a regression.

e2e on vehicles_312px.mp4 (538 frames, rfdetr-seg-nano TRT, mean of 3):
  ON  (default): 98.57 fps
  OFF (env=false): 76.60 fps
  Δ: +28.7% / −2.90 ms/frame

- Introduced `triton_jit_fallback.py` to detect Triton JIT compilation failures and log warnings.
- Updated `common.py` and `triton_preprocess_runtime.py` to utilize the new fallback mechanisms, ensuring graceful degradation to reference paths on failure.
- Added unit tests for Triton JIT failure detection and fallback behavior to ensure robustness.

- Added handling for OutOfResources exceptions in `triton_jit_fallback.py`.
- Updated the `is_triton_jit_failure` function to include OutOfResources in its checks.
- Introduced new unit tests to verify detection of OutOfResources errors and related messages.

- Added 'opsx/' and '.cursor/' to the .gitignore file to prevent tracking of these directories.
- Ensured proper formatting by adding a newline at the end of the file.

- Updated exception handling to define `_TRITON_JIT_EXCEPTION_TYPES` as a tuple of `_PTXASError` and `_OutOfResources`.
- Ensured that the exception types are set to an empty tuple in case of an ImportError, improving clarity and robustness of the error handling logic.