Commits

Commit history

1. Commits on Aug 10, 2026

   • feat: update llama.cpp to 936918514 (#2348)

     Show description for 67014fd
     abetlen

     authored
     67014fdView commit details

     Copy full SHA for 67014fd

     View code at this pointBrowse repository at this point
2. Commits on Jun 22, 2026

   • fix: preserve recurrent/hybrid model state when the full prompt is already cached (#2306)

     Show description for 9be3cd1
     

     allthatido

     and

     Ankur Kaul

     authored
     9be3cd1View commit details

     Copy full SHA for 9be3cd1

     View code at this pointBrowse repository at this point
3. Commits on Jun 2, 2026

   • fix: handle additional `from_pretrained` files in subfolders (#2085)

     Show description for d185d64
     

     TNing

     and

     abetlen

     authored
     d185d64View commit details

     Copy full SHA for d185d64

     View code at this pointBrowse repository at this point
4. Commits on Jun 1, 2026

   • fix: clear prompt for recurrent / hybrid models when only a partial prefix matches (#2108)

     Show description for cdb7a75
     

     avion23

     and

     Ralf Waldukat

     authored
     cdb7a75View commit details

     Copy full SHA for cdb7a75

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

   • fix(embedding): set kv_unified=True when embedding=True to enable batch processing (#2217)

     Show description for 95ccb19
     

     SanjanaB123

     and

     abetlen

     authored
     95ccb19View commit details

     Copy full SHA for 95ccb19

     View code at this pointBrowse repository at this point
6. Commits on May 11, 2026

   • fix(embed): mark all tokens as output to suppress llama.cpp 'overriding' INFO (#2208) (#2212)

     Anai-Guo

     authored
     f8c1f36View commit details

     Copy full SHA for f8c1f36

     View code at this pointBrowse repository at this point
7. Commits on May 8, 2026

   • fix: configure n_seq_max for batched embeddings (#2206)

     Show description for 128c331
     abetlen

     authored
     128c331View commit details

     Copy full SHA for 128c331

     View code at this pointBrowse repository at this point
8. Commits on Apr 3, 2026

   • fix(misc): replace deprecated llama.cpp references (#2170)

     Show description for 08e088c
     abetlen

     authored
     08e088cView commit details

     Copy full SHA for 08e088c

     View code at this pointBrowse repository at this point
9. Commits on Mar 24, 2026

   • feat: expose attention_type parameter in Llama.__init__ (#2143)

     Show description for 7b38c31
     

     3 peopleauthored
     7b38c31View commit details

     Copy full SHA for 7b38c31

     View code at this pointBrowse repository at this point
10. Commits on Mar 23, 2026

    • fix: Qwen 3.5 support (#2152)

      Show description for 11e7a55
      abetlen

      authored
      11e7a55View commit details

      Copy full SHA for 11e7a55

      View code at this pointBrowse repository at this point

    • feat: Update llama.cpp to ggerganov/llama.cpp@49bfddeca18e62fa3d39114a23e9fcbdf8a22388 (#2151)

      Show description for 18aa31e
      abetlen

      authored
      18aa31eView commit details

      Copy full SHA for 18aa31e

      View code at this pointBrowse repository at this point
11. Commits on Mar 22, 2026

    • misc: Add Ruff formatting (#2148)

      Show description for a9b4a06
      abetlen

      authored
      a9b4a06View commit details

      Copy full SHA for a9b4a06

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

    • fix: rename op_offloat to op_offload in llama.py (#2046)

      sergey21000

      authored
      30ddd56View commit details

      Copy full SHA for 30ddd56

      View code at this pointBrowse repository at this point
13. Commits on Jul 5, 2025

    • fix: Update reference to in Llama.embed. Closes #2037

      abetlen

      committed
      9e5a4eaView commit details

      Copy full SHA for 9e5a4ea

      View code at this pointBrowse repository at this point
14. Commits on Jul 1, 2025

    • fix(minor): Fix type hint for older versions of python

      abetlen

      committed
      5a635f4View commit details

      Copy full SHA for 5a635f4

      View code at this pointBrowse repository at this point

    • misc: Fix support for new parameters, deprecate rpc_servers parameter

      abetlen

      committed
      51dce74View commit details

      Copy full SHA for 51dce74

      View code at this pointBrowse repository at this point

    • feat: Update llama.cpp

      abetlen

      committed
      0d475d7View commit details

      Copy full SHA for 0d475d7

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

    • fix: error showing time spent in llama perf context print (#1898)

      Show description for 4442ff8
      

      shakalaca

      and

      abetlen

      authored
      4442ff8View commit details

      Copy full SHA for 4442ff8

      View code at this pointBrowse repository at this point

    • feat: Update llama.cpp

      abetlen

      committed
      80be68aView commit details

      Copy full SHA for 80be68a

      View code at this pointBrowse repository at this point
16. Commits on Dec 6, 2024

    • fix logit-bias type hint (#1802)

      Show description for fa04cdc
      ddh0

      authored
      fa04cdcView commit details

      Copy full SHA for fa04cdc

      View code at this pointBrowse repository at this point

    • fix: Fix pickling of Llama class by setting seed from _seed member. Closes #1769

      abetlen

      committed
      2523472View commit details

      Copy full SHA for 2523472

      View code at this pointBrowse repository at this point
17. Commits on Oct 31, 2024

    • feat: Update llama.cpp

      abetlen

      committed
      e712cffView commit details

      Copy full SHA for e712cff

      View code at this pointBrowse repository at this point
18. Commits on Sep 26, 2024

    • fix: Additional fixes for speculative decoding

      abetlen

      committed
      e975dabView commit details

      Copy full SHA for e975dab

      View code at this pointBrowse repository at this point

    • misc: Rename all_text to remaining_text (#1658)

      Show description for 11d9562
      

      xu-song

      and

      abetlen

      authored
      11d9562View commit details

      Copy full SHA for 11d9562

      View code at this pointBrowse repository at this point

    • fix: Fix speculative decoding

      abetlen

      committed
      9992c50View commit details

      Copy full SHA for 9992c50

      View code at this pointBrowse repository at this point
19. Commits on Sep 20, 2024

    • feat: Add option to configure n_ubatch

      abetlen

      committed
      6c44a3fView commit details

      Copy full SHA for 6c44a3f

      View code at this pointBrowse repository at this point
20. Commits on Sep 19, 2024

    • feat: Add loading sharded GGUF files from HuggingFace with Llama.from_pretrained(additional_files=[...]) . Closes #1341

      Show description for 84c0920
      

      Gnurro

      and

      abetlen

      authored
      84c0920View commit details

      Copy full SHA for 84c0920

      View code at this pointBrowse repository at this point

    • fix: Don't store scores internally unless logits_all=True. Reduces memory requirements for large context. Closes #1542

      abetlen

      committed
      29afcfdView commit details

      Copy full SHA for 29afcfd

      View code at this pointBrowse repository at this point

    • fix: Fix memory allocation of ndarray (#1704)

      Show description for 22cedad
      

      xu-song

      and

      abetlen

      authored
      22cedadView commit details

      Copy full SHA for 22cedad

      View code at this pointBrowse repository at this point

    • misc: Format

      abetlen

      committed
      9b64bb5View commit details

      Copy full SHA for 9b64bb5

      View code at this pointBrowse repository at this point

    • feat: Update sampling API for llama.cpp (#1742)

      Show description for f8fcb3e
      abetlen

      authored
      f8fcb3eView commit details

      Copy full SHA for f8fcb3e

      View code at this pointBrowse repository at this point
21. Commits on Aug 31, 2024

    • feat: Update llama.cpp

      abetlen

      committed
      9769e57View commit details

      Copy full SHA for 9769e57

      View code at this pointBrowse repository at this point
22. Commits on Aug 29, 2024

    • feat: Enable detokenizing special tokens with `special=True` (#1596)

      Show description for d981d32
      

      benniekiss

      and

      abetlen

      authored
      d981d32View commit details

      Copy full SHA for d981d32

      View code at this pointBrowse repository at this point
23. Commits on Aug 15, 2024

    • fix: Llama.close didn't free lora adapter (#1679)

      jkawamoto

      authored
      3c7501bView commit details

      Copy full SHA for 3c7501b

      View code at this pointBrowse repository at this point

    • feat: Update llama.cpp

      abetlen

      committed
      63d65acView commit details

      Copy full SHA for 63d65ac

      View code at this pointBrowse repository at this point