Myelin NVRTC compilation failure on Jetson Thor (SM110) building Fast-FoundationStereo - reproduces on TRT 10.14.1 and 11.2.1.2

Title: Myelin NVRTC compilation failure on Jetson Thor (SM110) building Fast-FoundationStereo — reproduces on TRT 10.14.1 and 11.2.1.2

Environment

• Jetson Thor (SM110), JetPack 7 / L4T, unified memory 122 GB
• TensorRT 10.14.1 (JetPack tarball trtexec) and 11.2.1.2 (pip tensorrt cu13 aarch64, python API)
• Model: Fast-FoundationStereo, exported from the NGC checkpoint (nvidia/tao/fast-foundationstereo v1.2, model_best_bp2_serialize.pth) with the official scripts/make_single_onnx.py (NVlabs/Fast-FoundationStereo, opset 17), --height 288 --width 480 --valid_iters 4, exporter run in nvcr.io/nvidia/pytorch:25.06-py3-igpu

Failure (identical on both TRT versions, fp32 — no precision flags involved)

TRT 10.14.1:

Error[9]: Skipping tactic 0x0 due to exception [myelin_graph.h:1182] MyelinCheckException:
nvrtc_compile.cpp:1118: CHECK(success) failed. NVRTC Compilation failure
Error[10]: IBuilder::buildSerializedNetworkToStream: Error Code 10: Internal Error
(Could not find any implementation for node {ForeignNode[/Concat.../Unsqueeze_166]}.)

TRT 11.2.1.2:

MyelinCheckException: nvrtc_compile.cpp:1122: CHECK(success) failed. NVRTC Compilation failure
Error Code 10: Internal Error (Could not find any implementation for node {ForeignNode[/Concat.../Cast_118]}.)

Additional data points

• An older single-ONNX export of the same model (576x960, iters_8, exported ~May 2026 with an older torch) builds and runs correctly in fp32 on the same machine/TRT 10.14.1 (1199 ms) — the failure is specific to graph patterns emitted by the newer exporter/torch.
• fp16 builds of the older export segfault the TRT compiler on SM110 (10.13.3 and 10.14.1; July 2026 finding).
• Full FoundationStereo-S (NGC dynamic ONNX) at 288x480 builds fp32 on 10.14.1 (1052 ms) — so small dims per se are fine.
• Looks related to #4715 (sm_120: Myelin "no valid tactics" on Fast-FS post_runner at all precisions, fused 3D-ConvTranspose/Cast pattern).

Questions

1. Is there a fix or workaround for the SM110 Myelin/NVRTC codegen failure (builder flags, tactic source restrictions, graph rewrites)?
2. Is the repo's plugin path (make_plugin_onnx.py + cpp plugin) the intended deployment route on Thor today?
3. Is fp16 expected to work for this model on SM110, given the exporter's own printed recipe suggests trtexec --fp16?

Full build logs and both ONNX files available on request.

Start by reproducing the failure with the newer ONNX export from scripts/make_single_onnx.py using trtexec or the Python API, then compare it with the older working export. Read related issue #4715 and inspect the make_plugin_onnx.py and C++ plugin path mentioned in the report. Done means a confirmed fix or workaround, with the expected fp16 and plugin deployment behavior documented.