Commits

Commit history

1. Commits on Dec 15, 2025

   • llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)

     Show description for b1f3a6e
     JohannesGaessler

     authored
     b1f3a6eView commit details

     Copy full SHA for b1f3a6e

     View code at this pointBrowse repository at this point
2. Commits on Dec 6, 2025

   • llama : remove quantization sanity check (#17788)

     Show description for 444f00b
     danbev

     authored
     444f00bView commit details

     Copy full SHA for 444f00b

     View code at this pointBrowse repository at this point
3. Commits on Dec 4, 2025

   • llama : fix sanity checks during quantization (#17721)

     ggerganov

     authored
     a67ef0fView commit details

     Copy full SHA for a67ef0f

     View code at this pointBrowse repository at this point
4. Commits on Nov 28, 2025

   • model : Qwen3 Next (#16095)

     Show description for ff55414
     

     3 peopleauthored
     ff55414View commit details

     Copy full SHA for ff55414

     View code at this pointBrowse repository at this point
5. Commits on Oct 30, 2025

   • llama : use std::abs instead of abs (#16853)

     kaetemi

     authored
     d739511View commit details

     Copy full SHA for d739511

     View code at this pointBrowse repository at this point
6. Commits on Oct 15, 2025

   • llama-quant: add support for mmproj (#16592)

     Show description for 3e3cb19
     

     ngxson

     and

     ggerganov

     authored
     3e3cb19View commit details

     Copy full SHA for 3e3cb19

     View code at this pointBrowse repository at this point
7. Commits on Sep 17, 2025

   • llama-quant : fix the verification of attention layers for encoder-decoder models (#16023)

     Show description for 745cbcf
     DamonFool

     authored
     745cbcfView commit details

     Copy full SHA for 745cbcf

     View code at this pointBrowse repository at this point
8. Commits on Sep 11, 2025

   • nitpick : correct MB to MiB (#15934)

     Show description for df082f5
     ddh0

     authored
     df082f5View commit details

     Copy full SHA for df082f5

     View code at this pointBrowse repository at this point
9. Commits on Aug 7, 2025

   • convert : support non-mxfp4 HF model (#15153)

     Show description for 50aa938
     ngxson

     authored
     50aa938View commit details

     Copy full SHA for 50aa938

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

    • llama : add gpt-oss (#15091)

      Show description for fd1234c
      

      3 peopleauthored
      fd1234cView commit details

      Copy full SHA for fd1234c

      View code at this pointBrowse repository at this point
11. Commits on Jul 31, 2025

    • quantize : skip tensor override when in fallback mode (#14995)

      EAddario

      authored
      daf2dd7View commit details

      Copy full SHA for daf2dd7

      View code at this pointBrowse repository at this point
12. Commits on Jul 13, 2025

    • quantize : fix minor logic flaw in --tensor-type (#14572)

      EAddario

      authored
      982e347View commit details

      Copy full SHA for 982e347

      View code at this pointBrowse repository at this point
13. Commits on Jul 11, 2025

    • model : support LiquidAI LFM2 hybrid family (#14620)

      Show description for f5e96b3
      

      Tarek Dakhran

      authored
      f5e96b3View commit details

      Copy full SHA for f5e96b3

      View code at this pointBrowse repository at this point
14. Commits on Jun 26, 2025

    • model : gemma3n text-only (#14400)

      Show description for 8846aac
      ngxson

      authored
      8846aacView commit details

      Copy full SHA for 8846aac

      View code at this pointBrowse repository at this point
15. Commits on Jun 22, 2025

    • quantize : handle user-defined pruning of whole layers (blocks) (#13037)

      EAddario

      authored
      fa4a9f2View commit details

      Copy full SHA for fa4a9f2

      View code at this pointBrowse repository at this point
16. Commits on Jun 15, 2025

    • quantize : change int to unsigned int for KV overrides (#14197)

      EAddario

      authored
      30e5b01View commit details

      Copy full SHA for 30e5b01

      View code at this pointBrowse repository at this point
17. Commits on May 13, 2025

    • quantize : improve tensor-type pattern matching (#13033)

      EAddario

      authored
      e5c834fView commit details

      Copy full SHA for e5c834f

      View code at this pointBrowse repository at this point
18. Commits on May 12, 2025

    • llama/ggml: add LLM training support (#10544)

      Show description for 10d2af0
      JohannesGaessler

      authored
      10d2af0View commit details

      Copy full SHA for 10d2af0

      View code at this pointBrowse repository at this point
19. Commits on Apr 13, 2025

    • quantize: Handle user-defined quantization levels for additional tensors (#12511)

      Show description for 71e90e8
      EAddario

      authored
      71e90e8View commit details

      Copy full SHA for 71e90e8

      View code at this pointBrowse repository at this point
20. Commits on Apr 2, 2025

    • llama : add option to override model tensor buffers (#11397)

      Show description for e0e912f
      slaren

      authored
      e0e912fView commit details

      Copy full SHA for e0e912f

      View code at this pointBrowse repository at this point
21. Commits on Mar 17, 2025

    • llama: Add support for RWKV v7 architecture (#12412)

      Show description for 7dfad38
      MollySophia

      authored
      7dfad38View commit details

      Copy full SHA for 7dfad38

      View code at this pointBrowse repository at this point
22. Commits on Jan 16, 2025

    • llama : add `llama_model_load_from_splits` (#11255)

      Show description for 681149c
      ngxson

      authored
      681149cView commit details

      Copy full SHA for 681149c

      View code at this pointBrowse repository at this point
23. Commits on Jan 12, 2025

    • llama : add `llama_vocab`, functions -> methods, naming (#11110)

      Show description for afa8a9e
      

      ggerganov

      and

      slaren

      authored
      afa8a9eView commit details

      Copy full SHA for afa8a9e

      View code at this pointBrowse repository at this point
24. Commits on Jan 10, 2025

    • llama: add support for QRWKV6 model architecture (#11001)

      Show description for ee7136c
      

      3 peopleauthored
      ee7136cView commit details

      Copy full SHA for ee7136c

      View code at this pointBrowse repository at this point
25. Commits on Jan 8, 2025

    • llama : avoid hardcoded QK_K (#11061)

      Show description for c07d437
      ggerganov

      authored
      c07d437View commit details

      Copy full SHA for c07d437

      View code at this pointBrowse repository at this point
26. Commits on Jan 7, 2025

    • GGUF: C++ refactor, backend support, misc fixes (#11030)

      Show description for 53ff6b9
      JohannesGaessler

      authored
      53ff6b9View commit details

      Copy full SHA for 53ff6b9

      View code at this pointBrowse repository at this point
27. Commits on Jan 6, 2025

    • llama : use _impl suffix instead of _internal (#11060)

      Show description for 5047dd3
      ggerganov

      authored
      5047dd3View commit details

      Copy full SHA for 5047dd3

      View code at this pointBrowse repository at this point
28. Commits on Jan 3, 2025

    • llama : refactor `src/llama.cpp` (#10902)

      Show description for f66f582
      ggerganov

      authored
      f66f582View commit details

      Copy full SHA for f66f582

      View code at this pointBrowse repository at this point
29. Loading