Commits

Commit history

1. Commits on Aug 27, 2026

   • [tests] remove quanto tests. (#14254)

     Show description for daad99a
     sayakpaul

     authored
     daad99aView commit details

     Copy full SHA for daad99a

     View code at this pointBrowse repository at this point
2. Commits on Aug 25, 2026

   • [core] pass diffusers library name to kernels calls (#14441)

     Show description for 95c0d46
     sayakpaul

     authored
     95c0d46View commit details

     Copy full SHA for 95c0d46

     View code at this pointBrowse repository at this point
3. Commits on Aug 18, 2026

   • [tests] refactor pipeline-level quantization tests (#14435)

     Show description for 425b113
     

     3 peopleauthored
     425b113View commit details

     Copy full SHA for 425b113

     View code at this pointBrowse repository at this point
4. Commits on Aug 3, 2026

   • [kernels] download kernels when users request for it. (#14298)

     Show description for 3533886
     sayakpaul

     authored
     3533886View commit details

     Copy full SHA for 3533886

     View code at this pointBrowse repository at this point
5. Commits on Aug 1, 2026

   • gguf: fix dequantization. (#14333)

     sayakpaul

     authored
     af0e6e4View commit details

     Copy full SHA for af0e6e4

     View code at this pointBrowse repository at this point
6. Commits on Jul 30, 2026

   • [quantization] SDNQ core loading (#14277)

     Show description for 8b33b47
     

     asomoza

     and

     sayakpaul

     authored
     8b33b47View commit details

     Copy full SHA for 8b33b47

     View code at this pointBrowse repository at this point

   • [tests] unify keep_in_32 tests in quantization test suites (#14257)

     Show description for 3c46892
     sayakpaul

     authored
     3c46892View commit details

     Copy full SHA for 3c46892

     View code at this pointBrowse repository at this point
7. Commits on Jul 21, 2026

   • Remove JAX/Flax (#14169)

     Show description for 80bfe77
     DN6

     authored
     80bfe77View commit details

     Copy full SHA for 80bfe77

     View code at this pointBrowse repository at this point
8. Commits on Jul 17, 2026

   • [Quantization] Fix ModelOpt pre-quantized loading (#14188)

     Show description for 48fadcc
     

     yzhautouskay

     and

     sayakpaul

     authored
     48fadccView commit details

     Copy full SHA for 48fadcc

     View code at this pointBrowse repository at this point
9. Commits on Jul 14, 2026

   • Add Nunchaku Lite single-file quantization (#14100)

     Show description for 60ec6f7
     

     5 peopleauthored
     60ec6f7View commit details

     Copy full SHA for 60ec6f7

     View code at this pointBrowse repository at this point
10. Commits on Jun 30, 2026

    • [chore] update to 2026 finally. (#14079)

      Show description for 4f37263
      sayakpaul

      authored
      4f37263View commit details

      Copy full SHA for 4f37263

      View code at this pointBrowse repository at this point
11. Commits on Jun 23, 2026

    • Enable BitsAndBytes quantization in MPS (#13915)

      Show description for e97a1ad
      

      LucasSte

      and

      sayakpaul

      authored
      e97a1adView commit details

      Copy full SHA for e97a1ad

      View code at this pointBrowse repository at this point
12. Commits on Jun 12, 2026

    • Incorporate safetensors support to TorchAO (#13719)

      Show description for 0b83812
      

      3 peopleauthored
      0b83812View commit details

      Copy full SHA for 0b83812

      View code at this pointBrowse repository at this point
13. Commits on Jun 10, 2026

    • Integrate AutoRound into Diffusers (#13552)

      Show description for c31bb1c
      

      4 peopleauthored
      c31bb1cView commit details

      Copy full SHA for c31bb1c

      View code at this pointBrowse repository at this point
14. Commits on May 20, 2026

    • fix(gguf): correct mismatched-shape error message in check_quantized_param_shape (#13504)

      Show description for 6a65a37
      Ricardo-M-L

      authored
      6a65a37View commit details

      Copy full SHA for 6a65a37

      View code at this pointBrowse repository at this point
15. Commits on May 18, 2026

    • Implement _dequantize for TorchAO quantizer (#13538)

      Show description for 907c0c2
      

      jiqing-feng

      and

      sayakpaul

      authored
      907c0c2View commit details

      Copy full SHA for 907c0c2

      View code at this pointBrowse repository at this point
16. Commits on May 13, 2026

    • Fix GGUF to Work Better with `modules_to_not_convert` / `keep_in_fp32_modules` (#13697)

      Show description for 40a43dd
      

      dg845

      and

      yiyixuxu

      authored
      40a43ddView commit details

      Copy full SHA for 40a43dd

      View code at this pointBrowse repository at this point
17. Commits on Apr 6, 2026

    • Remove references to torchao's AffineQuantizedTensor (#13405)

      Show description for 24b4c25
      

      andrewor14

      and

      sayakpaul

      authored
      24b4c25View commit details

      Copy full SHA for 24b4c25

      View code at this pointBrowse repository at this point
18. Commits on Mar 28, 2026

    • change minimum version guard for torchao to 0.15.0 (#13355)

      howardzhang-cv

      authored
      f2be8bdView commit details

      Copy full SHA for f2be8bd

      View code at this pointBrowse repository at this point
19. Commits on Mar 27, 2026

    • remove str option for quantization config in torchao (#13291)

      Show description for 1fe2125
      

      3 peopleauthored
      1fe2125View commit details

      Copy full SHA for 1fe2125

      View code at this pointBrowse repository at this point
20. Commits on Mar 11, 2026

    • [Quantization] Deprecate Quanto (#13180)

      Show description for 897aed7
      DN6

      authored
      897aed7View commit details

      Copy full SHA for 897aed7

      View code at this pointBrowse repository at this point
21. Commits on Feb 20, 2026

    • [gguf][torch.compile time] Convert to plain tensor earlier in dequantize_gguf_tensor (#13166)

      Show description for 01de02e
      anijain2305

      authored
      01de02eView commit details

      Copy full SHA for 01de02e

      View code at this pointBrowse repository at this point
22. Commits on Feb 13, 2026

    • Sunset Python 3.8 & get rid of explicit `typing` exports where possible (#12524)

      Show description for 2843b3d
      

      sayakpaul

      and

      DN6

      authored
      2843b3dView commit details

      Copy full SHA for 2843b3d

      View code at this pointBrowse repository at this point
23. Commits on Feb 11, 2026

    • [CI] Refactor Wan Model Tests (#13082)

      Show description for c3a4cd1
      DN6

      authored
      c3a4cd1View commit details

      Copy full SHA for c3a4cd1

      View code at this pointBrowse repository at this point
24. Commits on Feb 6, 2026

    • GGUF fix for unquantized types when using unquantize kernels (#12498)

      Show description for ca79f8c
      

      dxqb

      and

      yiyixuxu

      authored
      ca79f8cView commit details

      Copy full SHA for ca79f8c

      View code at this pointBrowse repository at this point
25. Commits on Jan 28, 2026

    • remove torchao autoquant from diffusers docs (#13048)

      Show description for 74a0f0b
      vkuzo

      authored
      74a0f0bView commit details

      Copy full SHA for 74a0f0b

      View code at this pointBrowse repository at this point
26. Commits on Jan 9, 2026

    • Torchao floatx version guard (#12923)

      Show description for 2f66edc
      

      howardzhang-cv

      and

      sayakpaul

      authored
      2f66edcView commit details

      Copy full SHA for 2f66edc

      View code at this pointBrowse repository at this point
27. Commits on Dec 30, 2025

    • fix torchao quantizer for new torchao versions (#12901)

      Show description for 1cdb872
      

      vkuzo

      and

      github-actions[bot]

      authored
      1cdb872View commit details

      Copy full SHA for 1cdb872

      View code at this pointBrowse repository at this point
28. Commits on Dec 8, 2025

    • Update the TensorRT-ModelOPT to Nvidia-ModelOPT (#12793)

      Show description for 5a74319
      

      jingyu-ml

      and

      sayakpaul

      authored
      5a74319View commit details

      Copy full SHA for 5a74319

      View code at this pointBrowse repository at this point
29. Commits on Sep 29, 2025

    • [quantization] feat: support aobaseconfig classes in `TorchAOConfig` (#12275)

      Show description for 64a5187
      

      sayakpaul

      and

      stevhliu

      authored
      64a5187View commit details

      Copy full SHA for 64a5187

      View code at this pointBrowse repository at this point
30. Commits on Sep 10, 2025

    • [quant] allow `components_to_quantize` to be a non-list for single components (#12234)

      Show description for eb7ef26
      

      sayakpaul

      and

      stevhliu

      authored
      eb7ef26View commit details

      Copy full SHA for eb7ef26

      View code at this pointBrowse repository at this point
31. Commits on Sep 9, 2025

    • gguf new quant type support (with demo) (#12076)

      Show description for 28106fc
      

      calcuis

      and

      github-actions[bot]

      authored
      28106fcView commit details

      Copy full SHA for 28106fc

      View code at this pointBrowse repository at this point
32. Commits on Sep 3, 2025

    • [Quantization] Add TRT-ModelOpt as a Backend (#11173)

      Show description for 4acbfbf
      

      ishan-modi

      and

      sayakpaul

      authored
      4acbfbfView commit details

      Copy full SHA for 4acbfbf

      View code at this pointBrowse repository at this point
33. Commits on Aug 14, 2025

    • support `hf_quantizer` in cache warmup. (#12043)

      Show description for 58bf268
      sayakpaul

      authored
      58bf268View commit details

      Copy full SHA for 58bf268

      View code at this pointBrowse repository at this point
34. Commits on Aug 5, 2025

    • Add cuda kernel support for GGUF inference (#11869)

      Show description for ba2ba90
      

      Isotr0py

      and

      DN6

      authored
      ba2ba90View commit details

      Copy full SHA for ba2ba90

      View code at this pointBrowse repository at this point