Commits

Commit history

1. Commits on Jun 1, 2026

   • feat: add Gemma 4 multimodal chat support (#2241)

     abetlen

     authored
     a9b480fView commit details

     Copy full SHA for a9b480f

     View code at this pointBrowse repository at this point

   • chore: bump version to 0.3.24 (#2236)

     abetlen

     authored
     26633bdView commit details

     Copy full SHA for 26633bd

     View code at this pointBrowse repository at this point

   • server types: Move 'model' parameter to clarify it is used (#1786)

     Show description for c3adb35
     domdomegg

     authored
     c3adb35View commit details

     Copy full SHA for c3adb35

     View code at this pointBrowse repository at this point

   • 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

   • fix: correct typo in comments and settings description (#2121)

     Show description for 33bf9d2
     thecaptain789

     authored
     33bf9d2View commit details

     Copy full SHA for 33bf9d2

     View code at this pointBrowse repository at this point

   • fix: match Transformers `tojson` in chat template rendering (#1486)

     Show description for 84bc143
     

     CISC

     and

     abetlen

     authored
     84bc143View commit details

     Copy full SHA for 84bc143

     View code at this pointBrowse repository at this point

   • fix: use env var configured multimodal library override paths when loading shared libraries (#1782)

     Show description for 5848020
     

     navratil-matej

     and

     abetlen

     authored
     5848020View commit details

     Copy full SHA for 5848020

     View code at this pointBrowse repository at this point

   • feat: add Jinja2 loop controls to chat templates (#2018)

     Show description for e8ee64b
     

     handshape

     and

     abetlen

     authored
     e8ee64bView commit details

     Copy full SHA for e8ee64b

     View code at this pointBrowse repository at this point
2. Commits on May 31, 2026

   • fix: avoid cleanup errors for partially initialized LlamaModel (#2173)

     Show description for fdf38b3
     

     usernames122

     and

     abetlen

     authored
     fdf38b3View commit details

     Copy full SHA for fdf38b3

     View code at this pointBrowse repository at this point

   • fix: suppress stdout and stderr in Jupyter notebooks (#2181)

     Show description for 6bdab5d
     Anai-Guo

     authored
     6bdab5dView commit details

     Copy full SHA for 6bdab5d

     View code at this pointBrowse repository at this point

   • Fix: model fails to load when chat template uses HuggingFace generation tags (#2226)

     Show description for f160bf7
     

     tobocop2

     and

     abetlen

     authored
     f160bf7View commit details

     Copy full SHA for f160bf7

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

   • feat: Update llama.cpp to b9a2170fc (#2223)

     abetlen

     authored
     5dd9b1cView commit details

     Copy full SHA for 5dd9b1c

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

   • feat: Update llama.cpp to ggerganov/llama.cpp@91e84fed6 (#2218)

     Show description for 7664a3e
     abetlen

     authored
     7664a3eView commit details

     Copy full SHA for 7664a3e

     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

   • chore: bump version to 0.3.23 (#2215)

     abetlen

     authored
     4a1a8ecView commit details

     Copy full SHA for 4a1a8ec

     View code at this pointBrowse repository at this point

   • 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

   • feat: update llama.cpp to 5d6f18a63 (#2207)

     abetlen

     authored
     f774690View commit details

     Copy full SHA for f774690

     View code at this pointBrowse repository at this point

   • 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 May 4, 2026

   • fix(_internals): use n_tokens0 offset when enabling last-token logits in add_sequence (#2205)

     Show description for 90e8df9
     Anai-Guo

     authored
     90e8df9View commit details

     Copy full SHA for 90e8df9

     View code at this pointBrowse repository at this point
9. Commits on May 2, 2026

   • chore: bump version to 0.3.22 (#2200)

     abetlen

     authored
     9cf0ce7View commit details

     Copy full SHA for 9cf0ce7

     View code at this pointBrowse repository at this point
10. Commits on Apr 27, 2026

    • chore: bump version to 0.3.21 (#2192)

      abetlen

      authored
      c8075d1View commit details

      Copy full SHA for c8075d1

      View code at this pointBrowse repository at this point

    • feat: Update llama.cpp to ggerganov/llama.cpp@f53577432 (#2189)

      Show description for d87bf08
      abetlen

      authored
      d87bf08View commit details

      Copy full SHA for d87bf08

      View code at this pointBrowse repository at this point
11. Commits on Apr 13, 2026

    • feat: Update llama.cpp to ggerganov/llama.cpp@227ed28e1 (#2182)

      abetlen

      authored
      1b1a320View commit details

      Copy full SHA for 1b1a320

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

    • feat: Update llama.cpp to ggerganov/llama.cpp@3bd9aa1f9 (#2176)

      Show description for 1bcc5bc
      abetlen

      authored
      1bcc5bcView commit details

      Copy full SHA for 1bcc5bc

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

    • chore: bump version to 0.3.20 (#2171)

      abetlen

      authored
      02d6beeView commit details

      Copy full SHA for 02d6bee

      View code at this pointBrowse repository at this point

    • 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

    • feat: Update llama.cpp to ggerganov/llama.cpp@f49e9178767d557a522618b16ce8694f9ddac628 (#2169)

      abetlen

      authored
      100b275View commit details

      Copy full SHA for 100b275

      View code at this pointBrowse repository at this point
14. Commits on Mar 30, 2026

    • feat(server): add model-load chat_template_kwargs (#2168)

      abetlen

      authored
      7257ba9View commit details

      Copy full SHA for 7257ba9

      View code at this pointBrowse repository at this point
15. Commits on Mar 25, 2026

    • Bump version to 0.3.19 (#2162)

      abetlen

      authored
      f54421bView commit details

      Copy full SHA for f54421b

      View code at this pointBrowse repository at this point

    • feat: Update llama.cpp to ggerganov/llama.cpp@c0159f9c1f874da15e94f371d136f5920b4b5335 (#2161)

      Show description for c670222
      abetlen

      authored
      c670222View commit details

      Copy full SHA for c670222

      View code at this pointBrowse repository at this point

    • fix: handle embedding models without KV memory (#2160)

      Show description for ac59e5a
      abetlen

      authored
      ac59e5aView commit details

      Copy full SHA for ac59e5a

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

    • chore: bump version (#2157)

      abetlen

      authored
      d6f46a5View commit details

      Copy full SHA for d6f46a5

      View code at this pointBrowse repository at this point

    • 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
17. Commits on Mar 23, 2026

    • chore: Bump version (#2153)

      abetlen

      authored
      a6b1807View commit details

      Copy full SHA for a6b1807

      View code at this pointBrowse repository at this point

    • 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