Commits

Commit history

1. Commits on May 18, 2026

   • Update Submodule vendor/llama.cpp 39cf5d6..a135ec0

     Show description for 58ce983
     JamePeng

     committed
     58ce983View commit details

     Copy full SHA for 58ce983

     Browse repository at this point

   • ci(metal): upgrade actions/download-artifact@v6 ->v7

     Show description for a96f280
     JamePeng

     committed
     a96f280View commit details

     Copy full SHA for a96f280

     Browse repository at this point
2. Commits on May 17, 2026

   • Bump version to 0.3.39

     Show description for a778c57
     JamePeng

     committed
     a778c57View commit details

     Copy full SHA for a778c57

     Browse repository at this point

   • docs(readme): update wheel requirements and dynamic CPU backend info

     Show description for e87041e
     JamePeng

     committed
     e87041eView commit details

     Copy full SHA for e87041e

     Browse repository at this point

   • Update Submodule vendor/llama.cpp b64739e..39cf5d6

     Show description for d33d988
     JamePeng

     committed
     d33d988View commit details

     Copy full SHA for d33d988

     Browse repository at this point

   • chore(docs): remove outdated mkdocs workflow

     Show description for ec580cb
     JamePeng

     committed
     ec580cbView commit details

     Copy full SHA for ec580cb

     Browse repository at this point

   • Update .gitmodules submodule git addr

     Show description for b8d69f2
     JamePeng

     committed
     b8d69f2View commit details

     Copy full SHA for b8d69f2

     Browse repository at this point

   • ci: Remove outdated workflow

     Show description for 6e32ef0
     JamePeng

     committed
     6e32ef0View commit details

     Copy full SHA for 6e32ef0

     Browse repository at this point

   • ci(cu12+linux): build CU124/126/128 wheels with GGML dynamic backends for linux

     Show description for 42891ef
     JamePeng

     committed
     42891efView commit details

     Copy full SHA for 42891ef

     Browse repository at this point

   • ci(cu131+linux): build CU131 wheels with GGML dynamic backends for linux

     Show description for a4c8d77
     JamePeng

     committed
     a4c8d77View commit details

     Copy full SHA for a4c8d77

     Browse repository at this point

   • fix(context): prevent operations on uninitialized or closed contexts

     Show description for 50627bf
     JamePeng

     committed
     50627bfView commit details

     Copy full SHA for 50627bf

     Browse repository at this point

   • Sync llama.cpp API 20260517

     Show description for 1278812
     JamePeng

     committed
     1278812View commit details

     Copy full SHA for 1278812

     Browse repository at this point

   • fix(_internals): Remove unnecessary free operations; models should not be released within the context.

     Show description for 39785d0
     JamePeng

     committed
     39785d0View commit details

     Copy full SHA for 39785d0

     Browse repository at this point
3. Commits on May 16, 2026

   • Update Submodule vendor/llama.cpp 49d1701..b64739e

     JamePeng

     committed
     e47843fView commit details

     Copy full SHA for e47843f

     Browse repository at this point

   • ci(cu12+windows): build CU124-128 wheels with GGML dynamic backends for windows

     Show description for df07219
     JamePeng

     committed
     df07219View commit details

     Copy full SHA for df07219

     Browse repository at this point

   • ci(cu131+windows): build CU131 wheels with GGML dynamic backends for windows

     Show description for 628373c
     JamePeng

     committed
     628373cView commit details

     Copy full SHA for 628373c

     Browse repository at this point

   • Bump version to 0.3.39-preview

     Show description for a8f928c
     JamePeng

     committed
     a8f928cView commit details

     Copy full SHA for a8f928c

     Browse repository at this point

   • feat(core): support loading GGML_BACKEND_DL dynamic backend libraries from wheel lib

     Show description for 038a953
     JamePeng

     committed
     038a953View commit details

     Copy full SHA for 038a953

     Browse repository at this point

   • fix(_ggml): correct `ggml_backend_unload` function name

     JamePeng

     committed
     6af3cd7View commit details

     Copy full SHA for 6af3cd7

     Browse repository at this point

   • build(cmake): clean up dev files and import libs from Windows wheels

     Show description for 4c4e3d0
     JamePeng

     committed
     4c4e3d0View commit details

     Copy full SHA for 4c4e3d0

     Browse repository at this point

   • build(cmake): sync llama build options and disable server UI

     Show description for 24b1dc8
     JamePeng

     committed
     24b1dc8View commit details

     Copy full SHA for 24b1dc8

     Browse repository at this point

   • build(cmake): refactor install target lists for new GGML backend layout

     Show description for 2dad6dc
     JamePeng

     committed
     2dad6dcView commit details

     Copy full SHA for 2dad6dc

     Browse repository at this point

   • docs(index): Append Logger.md info and link

     Show description for 43a96e2
     JamePeng

     committed
     43a96e2View commit details

     Copy full SHA for 43a96e2

     Browse repository at this point

   • docs(Logger.md): Upload Logger documentation

     Show description for 7eab8d3
     JamePeng

     committed
     7eab8d3View commit details

     Copy full SHA for 7eab8d3

     Browse repository at this point

   • docs(Llama.md): update `verbose=False` vs. `verbosity=0` note

     Show description for 1064cf1
     JamePeng

     committed
     1064cf1View commit details

     Copy full SHA for 1064cf1

     Browse repository at this point

   • Update SCHEMA.md

     JamePeng

     committed
     4fb0746View commit details

     Copy full SHA for 4fb0746

     Browse repository at this point

   • docs(README.md): Update the jump link for Qwen3-ASR in the top directory.

     Show description for 43b85f3
     JamePeng

     committed
     43b85f3View commit details

     Copy full SHA for 43b85f3

     Browse repository at this point

   • docs(README.md): add Qwen3-ASR documentation and usage example

     Show description for ad67e0e
     JamePeng

     committed
     ad67e0eView commit details

     Copy full SHA for ad67e0e

     Browse repository at this point

   • Implement `Qwen3ASRChatHandler` for `Qwen3-ASR` models.

     Show description for 4d3e320
     JamePeng

     committed
     4d3e320View commit details

     Copy full SHA for 4d3e320

     Browse repository at this point
4. Commits on May 15, 2026

   • Update Submodule vendor/llama.cpp 834a243..49d1701

     JamePeng

     committed
     c14d769View commit details

     Copy full SHA for c14d769

     Browse repository at this point
5. Commits on May 14, 2026

   • docs(wiki): document runtime verbosity and log filters for Llama

     Show description for d89aa5a
     JamePeng

     committed
     d89aa5aView commit details

     Copy full SHA for d89aa5a

     Browse repository at this point

   • feat(core): integrate fine-grained logging API into Llama class

     Show description for f64320d
     JamePeng

     committed
     f64320dView commit details

     Copy full SHA for f64320d

     Browse repository at this point

   • feat(logger): refactor and enhance ggml logging configuration system

     Show description for 1fb6a66
     JamePeng

     committed
     1fb6a66View commit details

     Copy full SHA for 1fb6a66

     Browse repository at this point

   • Update Submodule vendor/llama.cpp a9883db..834a243

     JamePeng

     committed
     0295d0cView commit details

     Copy full SHA for 0295d0c

     Browse repository at this point
6. Commits on May 13, 2026

   • fix(MTMDChatHandler): correct audio_url content type check and improve variable handling

     Show description for 9954393
     JamePeng

     committed
     9954393View commit details

     Copy full SHA for 9954393

     Browse repository at this point