Commit History

5 days ago

  1. Card and MEASUREMENTS.md: benchmark prefill counts are no longer called prompt lengths⁠

    Verified signature
    b509dff

8 days ago

  1. Mac rows for the files of 2026-11-12 (Apple M4 Max, LiteRT-LM 0.19.1: the int4 file on the GPU and the CPU, the int8 file on the CPU) in the card, MEASUREMENTS.md and litertlm_manifest.json

    Verified signature
    d0d8d73
  2. litertlm_manifest.json: both files with external weights (sha256, size, sections), min_runtime_version 0.19.0, the LiteRT-LM#3986 line

    Verified signature
    96c44fd
  3. Both files with LiteRT external weights (the same weights; an Android GPU needs LiteRT-LM 0.19.0 or later, the earlier files stay at revision ee03d010); card and MEASUREMENTS updated

    Verified signature
    b4ed353

9 days ago

  1. Correct three details in the card and MEASUREMENTS.md and make their wording clearer

    Verified signature
    ee03d01

10 days ago

  1. Add WeVisOne-VL-4B_int8.litertlm, the file for a CPU, with its card rows, measurements and manifest entry

    Verified signature
    f8ca054
  2. Card: the Android library run of a test app, this file against an int8 variant for the GPU in turns (2026-11-10), process count

    Verified signature
    872c152
  3. Card: shorter card; how the numbers were measured, raw values and earlier runs moved to MEASUREMENTS.md

    Verified signature
    2fcc2c1
  4. Card: library path, prompt file, cache files and how build B was made

    Verified signature
    90d80c1
  5. Add WeVisOne-VL-4B int4 LiteRT-LM file, model card and manifest

    Verified signature
    cfe3cff
  6. initial commit

    Verified signature
    0e6d6d6