Commit History
21 days ago
-
README: link the browser demo (static Space litert-community/moge-2-photo-to-3d; the GitHub Pages copy stays as the second link)
Verified signature6af93bb
-
Try-it link: demo now hosted at google-ai-edge.github.io/litert-samples
Verified signature5ad7d4e
-
Card: base_model_relation: quantized (list under the base model's Quantizations)
Verified signature8d953cc
-
Card: fp16 variant (numbers vs fp32, WebGPU use; keep fp32 for WASM)
Verified signature6e31a5b -
Add moge_fp16.tflite: fp16 weight-only cast (halves the download for GPU use)
Verified signature50f039e -
Add measured Raspberry Pi 5 (CPU) section
Verified signatureNumbers from the 2026-08-31 Raspberry Pi 5 sweep: LiteRT benchmark_model (litert-cli-nightly 0.2.0.dev20260805), CPU/XNNPACK, 4 threads, 10 warm-up + 50 timed runs x 3 invocations per file, cooldown between invocations, thermal throttle state verified 0x0 on every run. Median + spread, never single-shot. Measurements are joined to this repo by exact .tflite file name.19f3c2d
-
Add browser Try-it link (LiteRT.js demo at page-demos/moge)
Verified signaturea1695cf
-
Add measured Snapdragon NPU / GPU section (Galaxy S26)
Verified signatureNumbers from the 2026-08-23 Galaxy S26 sweep. Primary log: litertlm-convert/portal_work/bench_all.txt + bench_redo.txt, summarised in portal_work/NOTES.md (2026-08-23, the 50-model NPU/GPU comparison). Every row carries device, SoC, runtime, N and thermal state. Measurements are joined to this repo by exact .tflite file name.9ebfa56
-
Card: correct the GPU node counts — the previous figures added the XNNPACK fallback partition to the GPU delegate partition
Verified signature02b1982
-
Card: add a measured Performance table (Pixel 8a, benchmark_model GPU+CPU), naming the runtime for each row
Verified signaturef949b16
-
Add MoGe-2 ViT-S LiteRT GPU conversion (mirror of the verified release)
Verified signature3d25b36 -
initial commit
Verified signature207bd4f