Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: withcatai/node-llama-cpp
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: master@{1day}
Choose a base ref
...
head repository: withcatai/node-llama-cpp
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: master
Choose a head ref
  • 1 commit
  • 60 files changed
  • 1 contributor

Commits on May 17, 2025

  1. feat: save and restore a context sequence state (#460) 

    * feat: save and restore a context sequence state
* feat: stream function call parameters
* feat: configure Hugging Face remote endpoint for resolving URIs
* feat: Qwen 3 support
* feat(`QwenChatWrapper`): support discouraging the generation of thoughts
* feat(`getLlama`): `dryRun` option
* feat: `getLlamaGpuTypes` function
* fix: adapt to breaking `llama.cpp` changes
* fix: capture multi-token segment separators
* fix: race condition when reading extremely long gguf metadata
* fix: adapt memory estimation to new added model architectures
* fix: skip binary testing on certain problematic conditions
* fix: improve GPU backend loading error description
* fix: update gguf types
* fix: performance improvements
* docs: update the awesome list
* docs: solutions to more CUDA issues
    @giladgd
    giladgd authored May 17, 2025
    Configuration menu
    Copy the full SHA
    f2cb873 View commit details
    Browse the repository at this point in the history
Loading