Commits

Breadcrumbs

History for

onmain

User selector

All users

All time

Commit history

Commits on Jan 29, 2026

• [v4] Restructure repo to use pnpm workspaces (#1504)

  Show description for 4e1b4b6
  

  nico-martin

  and

  xenova

  authored
  4e1b4b6View commit details

  Copy full SHA for 4e1b4b6

  View code at this pointBrowse repository at this point

Commits on Dec 23, 2025

• [v4] Switch build system to esbuild (#1466)

  Show description for 760cc66
  

  nico-martin

  and

  xenova

  authored
  760cc66View commit details

  Copy full SHA for 760cc66

  View code at this pointBrowse repository at this point

Commits on Jul 30, 2025

• Upgrade to new WebGPU EP

  Show description for c6b7edf
  

  3 peopleauthored
  c6b7edfView commit details

  Copy full SHA for c6b7edf

  View code at this pointBrowse repository at this point

Commits on Jul 2, 2025

• Pin numpy version for quantization scripts (#1351)

  Show description for b1a8389
  

  fidoriel

  and

  xenova

  authored
  b1a8389View commit details

  Copy full SHA for b1a8389

  View code at this pointBrowse repository at this point

Commits on Mar 5, 2025

• Optimize encoder-decoder exports (including Whisper) (#1218)

  Show description for c1e0ed3
  xenova

  authored
  c1e0ed3View commit details

  Copy full SHA for c1e0ed3

  View code at this pointBrowse repository at this point

Commits on Feb 26, 2025

• Update conversion script versions (#1204)

  Show description for 8bef102
  xenova

  authored
  8bef102View commit details

  Copy full SHA for 8bef102

  View code at this pointBrowse repository at this point

Commits on Dec 2, 2024

• Add support for idefics3 (SmolVLM) (#1059)

  Show description for 11db949
  xenova

  authored
  11db949View commit details

  Copy full SHA for 11db949

  View code at this pointBrowse repository at this point

Commits on Nov 26, 2024

• Add new models (Janus, Qwen2-VL, JinaCLIP, LLaVA-OneVision, ViTPose, MGP-STR) & refactor processors. (#1001)

  Show description for e848907
  xenova

  authored
  e848907View commit details

  Copy full SHA for e848907

  View code at this pointBrowse repository at this point

Commits on Nov 25, 2024

• Add support for `--op_block_list` in quantization script (#1036)

  Show description for 5272b12
  

  pdufour

  and

  xenova

  authored
  5272b12View commit details

  Copy full SHA for 5272b12

  View code at this pointBrowse repository at this point

Commits on Nov 4, 2024

• Add support for OLMo models (#1011)

  Show description for ed94f6b
  xenova

  authored
  ed94f6bView commit details

  Copy full SHA for ed94f6b

  View code at this pointBrowse repository at this point

Commits on Nov 1, 2024

• Remove duplicate `gemma` value from NO_PER_CHANNEL_REDUCE_RANGE_MODELS set (#1005)

  Show description for 6bd45ac
  

  bekzod

  and

  xenova

  authored
  6bd45acView commit details

  Copy full SHA for 6bd45ac

  View code at this pointBrowse repository at this point

• Add support for MobileLLM (#1003)

  xenova

  authored
  bf1412eView commit details

  Copy full SHA for bf1412e

  View code at this pointBrowse repository at this point

Commits on Oct 9, 2024

• Remove in-library list of supported models

  xenova

  committed
  8b0d330View commit details

  Copy full SHA for 8b0d330

  View code at this pointBrowse repository at this point

• Add whisper turbo alignment heads

  xenova

  committed
  a32efa3View commit details

  Copy full SHA for a32efa3

  View code at this pointBrowse repository at this point

Commits on Sep 9, 2024

• Merge branch 'main' into v3

  xenova

  committed
  4f17e95View commit details

  Copy full SHA for 4f17e95

  View code at this pointBrowse repository at this point

• Bump `onnxruntime==1.19.2` in scripts/requirements.txt

  xenova

  committed
  ba58ea2View commit details

  Copy full SHA for ba58ea2

  View code at this pointBrowse repository at this point

Commits on Sep 2, 2024

• Wrap onnxslim with try block

  xenova

  committed
  ba5d725View commit details

  Copy full SHA for ba5d725

  View code at this pointBrowse repository at this point

• Add `library_name` option to convert.py

  xenova

  committed
  844099dView commit details

  Copy full SHA for 844099d

  View code at this pointBrowse repository at this point

Commits on Aug 28, 2024

• Fix scripts/requirements.txt

  xenova

  committed
  bf093aeView commit details

  Copy full SHA for bf093ae

  View code at this pointBrowse repository at this point

Commits on Aug 27, 2024

• Topologically sort fp16 nodes

  xenova

  committed
  1b7f978View commit details

  Copy full SHA for 1b7f978

  View code at this pointBrowse repository at this point

Commits on Aug 9, 2024

• Downgrade `onnxconverter-common`

  xenova

  committed
  83f5718View commit details

  Copy full SHA for 83f5718

  View code at this pointBrowse repository at this point

• Consolidate conversion and quantization script

  xenova

  committed
  12569b8View commit details

  Copy full SHA for 12569b8

  View code at this pointBrowse repository at this point

Commits on Jul 12, 2024

• Separate IO and Quantization args

  xenova

  committed
  974f086View commit details

  Copy full SHA for 974f086

  View code at this pointBrowse repository at this point

• Update converstion script requirements

  xenova

  committed
  9787b75View commit details

  Copy full SHA for 9787b75

  View code at this pointBrowse repository at this point

• Reload model for each quantization mode

  xenova

  committed
  9ef3a6dView commit details

  Copy full SHA for 9ef3a6d

  View code at this pointBrowse repository at this point

Commits on Jul 4, 2024

• correct attribute

  xenova

  committed
  cd1ea69View commit details

  Copy full SHA for cd1ea69

  View code at this pointBrowse repository at this point

• Fix q8 quantization for models > 2GB

  xenova

  committed
  04a334aView commit details

  Copy full SHA for 04a334a

  View code at this pointBrowse repository at this point

• Remove debug log

  xenova

  committed
  b411e9fView commit details

  Copy full SHA for b411e9f

  View code at this pointBrowse repository at this point

• formatting

  xenova

  committed
  23440f0View commit details

  Copy full SHA for 23440f0

  View code at this pointBrowse repository at this point

• Reorder functions

  xenova

  committed
  88f3e44View commit details

  Copy full SHA for 88f3e44

  View code at this pointBrowse repository at this point

• Use `check_and_save_model` for saving fp16 model

  xenova

  committed
  45cd8d4View commit details

  Copy full SHA for 45cd8d4

  View code at this pointBrowse repository at this point

• fp16 disable_shape_infer if model is too large

  xenova

  committed
  c835b54View commit details

  Copy full SHA for c835b54

  View code at this pointBrowse repository at this point

• save q4 quantization

  xenova

  committed
  83cbb21View commit details

  Copy full SHA for 83cbb21

  View code at this pointBrowse repository at this point

Commits on Jul 3, 2024

• Fix q4 quantization

  xenova

  committed
  9128651View commit details

  Copy full SHA for 9128651

  View code at this pointBrowse repository at this point

• update deps

  xenova

  committed
  04af3d5View commit details

  Copy full SHA for 04af3d5

  View code at this pointBrowse repository at this point