Commits

Commit history

1. Commits on May 4, 2026

   • Bump version to 0.3.38

     Show description for ef27f33
     JamePeng

     committed
     ef27f33View commit details

     Copy full SHA for ef27f33

     View code at this pointBrowse repository at this point

   • patch(logger): filter out verbose noisy CUDA Graph debug logs

     Show description for 22a7fdb
     JamePeng

     committed
     22a7fdbView commit details

     Copy full SHA for 22a7fdb

     View code at this pointBrowse repository at this point

   • perf: Optimize detokenize buffer sizing for CJK-heavy outputs

     Show description for a63f60e
     JamePeng

     committed
     a63f60eView commit details

     Copy full SHA for a63f60e

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

   • feat(grammar): sync JSON schema to GBNF converter with upstream

     Show description for 5336947
     JamePeng

     committed
     5336947View commit details

     Copy full SHA for 5336947

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

   • Bump version to 0.3.37

     Show description for fe38cbf
     JamePeng

     committed
     fe38cbfView commit details

     Copy full SHA for fe38cbf

     View code at this pointBrowse repository at this point
4. Commits on Apr 30, 2026

   • feat(llama): add fine-grained MoE CPU offloading controls

     Show description for b7064d7
     JamePeng

     committed
     b7064d7View commit details

     Copy full SHA for b7064d7

     View code at this pointBrowse repository at this point

   • feat(_ggml): implement ggml-backend API bindings and fix type hints

     Show description for 66dd88b
     JamePeng

     committed
     66dd88bView commit details

     Copy full SHA for 66dd88b

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

   • feat(handler): Support `add_generation_prompt` parameter pass to MTMDChatHandler

     Show description for 969b45f
     JamePeng

     committed
     969b45fView commit details

     Copy full SHA for 969b45f

     View code at this pointBrowse repository at this point
6. Commits on Apr 26, 2026

   • feat(core): implement thread-safe generation abort mechanism

     Show description for 2cccd2e
     JamePeng

     committed
     2cccd2eView commit details

     Copy full SHA for 2cccd2e

     View code at this pointBrowse repository at this point
7. Commits on Apr 24, 2026

   • feat(speculative): introduce O(1) hash-based N-Gram speculative decoding

     Show description for ddf577d
     JamePeng

     committed
     ddf577dView commit details

     Copy full SHA for ddf577d

     View code at this pointBrowse repository at this point
8. Commits on Apr 22, 2026

   • feat(types): introduce MCP definitions and align with latest OpenAI spec

     Show description for afd038f
     JamePeng

     committed
     afd038fView commit details

     Copy full SHA for afd038f

     View code at this pointBrowse repository at this point
9. Commits on Apr 21, 2026

   • Update Submodule vendor/llama.cpp 81df3f7..82209ef

     JamePeng

     committed
     8625836View commit details

     Copy full SHA for 8625836

     View code at this pointBrowse repository at this point
10. Commits on Apr 20, 2026

    • Update Submodule vendor/llama.cpp 037bfe3..81df3f7

      JamePeng

      committed
      e3b7ad6View commit details

      Copy full SHA for e3b7ad6

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

    • Update Submodule vendor/llama.cpp 9db77a0..45cac7c

      JamePeng

      committed
      7a19575View commit details

      Copy full SHA for 7a19575

      View code at this pointBrowse repository at this point
12. Commits on Apr 16, 2026

    • Bump version to 0.3.36

      Show description for b97cb63
      JamePeng

      committed
      b97cb63View commit details

      Copy full SHA for b97cb63

      View code at this pointBrowse repository at this point

    • feat: enhance Qwen35ChatHandler with preserve_thinking and Qwen3.6 template fixes

      Show description for 7820677
      JamePeng

      committed
      7820677View commit details

      Copy full SHA for 7820677

      View code at this pointBrowse repository at this point
13. Commits on Apr 15, 2026

    • Sync mtmd: add mtmd_image_tokens_get_decoder_pos() API (#21851)

      Show description for 9d2b2cb
      JamePeng

      committed
      9d2b2cbView commit details

      Copy full SHA for 9d2b2cb

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

    • docs: add audio processing recommendation to Gemma4ChatHandler

      Show description for 5e6529e
      JamePeng

      committed
      5e6529eView commit details

      Copy full SHA for 5e6529e

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

    • refactor: update Gemma4ChatHandler with latest google/gemma-4-31B-it chat template from huggingface

      Show description for 122d8db
      JamePeng

      committed
      122d8dbView commit details

      Copy full SHA for 122d8db

      View code at this pointBrowse repository at this point
16. Commits on Apr 9, 2026

    • fix missing change of llama_cpp.llama_split_mode.LLAMA_SPLIT_MODE_LAYER,

      JamePeng

      committed
      f22b819View commit details

      Copy full SHA for f22b819

      View code at this pointBrowse repository at this point

    • Sync ggml: backend-agnostic tensor parallelism (experimental) (#19378)

      JamePeng

      committed
      6866ebaView commit details

      Copy full SHA for 6866eba

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

    • Implement `Step3VLChatHandler` for Step3-VL-10B

      Show description for abe789f
      JamePeng

      committed
      abe789fView commit details

      Copy full SHA for abe789f

      View code at this pointBrowse repository at this point

    • Sync ggml: add Q1_0 1-bit quantization support (CPU) (#21273)

      JamePeng

      committed
      9241b0fView commit details

      Copy full SHA for 9241b0f

      View code at this pointBrowse repository at this point
18. Commits on Apr 7, 2026

    • feat(types): align with latest OpenAI API spec and fix type issues

      Show description for 645c8ed
      JamePeng

      committed
      645c8edView commit details

      Copy full SHA for 645c8ed

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

    • Bump version to 0.3.35

      Show description for e1ade17
      JamePeng

      committed
      e1ade17View commit details

      Copy full SHA for e1ade17

      View code at this pointBrowse repository at this point

    • fix: expand stop sequences for Gemma4ChatHandler

      Show description for d4fef6a
      JamePeng

      committed
      d4fef6aView commit details

      Copy full SHA for d4fef6a

      View code at this pointBrowse repository at this point

    • Relocate LFM25VLChatHandler, add comment details, and update README.md

      JamePeng

      committed
      d7478deView commit details

      Copy full SHA for d7478de

      View code at this pointBrowse repository at this point

    • prevent errors by setting 'image_min_tokens' to 256 if higher values are detected

      alcoftTAO

      committed
      00e67b8View commit details

      Copy full SHA for 00e67b8

      View code at this pointBrowse repository at this point
20. Commits on Apr 5, 2026

    • updated code

      alcoftTAO

      committed
      17366d3View commit details

      Copy full SHA for 17366d3

      View code at this pointBrowse repository at this point

    • Merge branch 'JamePeng:main' into lfm2.5-vl

      alcoftTAO

      authored
      5fc4588View commit details

      Copy full SHA for 5fc4588

      View code at this pointBrowse repository at this point

    • feat(types): align with latest OpenAI OpenAPI spec (audio, structured outputs)

      Show description for 1dc235f
      JamePeng

      committed
      1dc235fView commit details

      Copy full SHA for 1dc235f

      View code at this pointBrowse repository at this point
21. Commits on Apr 4, 2026

    • docs: clarify enable_thinking compatibility for Gemma 4 models

      Show description for 7bd7175
      JamePeng

      committed
      7bd7175View commit details

      Copy full SHA for 7bd7175

      View code at this pointBrowse repository at this point

    • Update llama_types.py OpenAI OpenAPI Link

      JamePeng

      committed
      6e99244View commit details

      Copy full SHA for 6e99244

      View code at this pointBrowse repository at this point

    • fix(Qwen35ChatHandler): Correct CHAT_FORMAT `tool_call` typo

      Show description for 10a6abd
      JamePeng

      committed
      10a6abdView commit details

      Copy full SHA for 10a6abd

      View code at this pointBrowse repository at this point

    • feat(chat_format): add Gemma 4 chat handler with multimodal and tool support

      Show description for a5b4762
      JamePeng

      committed
      a5b4762View commit details

      Copy full SHA for a5b4762

      View code at this pointBrowse repository at this point