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: v3.0.1
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
  • 18 commits
  • 252 files changed
  • 1 contributor

Commits on Sep 24, 2024

  1. fix: use a compressed logo image for README.md (#340)

    * fix: use a compressed logo image for `README.md`
    * build: switch to `latest` release of `llama.cpp`
    giladgd authored Sep 24, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    8ab983b View commit details
  2. docs: history (#341)

    giladgd authored Sep 24, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    106b171 View commit details
  3. fix(node template): bug (#342)

    giladgd authored Sep 24, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    1291b97 View commit details

Commits on Sep 25, 2024

  1. fix: increase semantic-release retires for GitHub API ratelimit (#343)

    giladgd authored Sep 25, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    4478fbf View commit details
  2. fix: adapt to llama.cpp breaking change (#344)

    giladgd authored Sep 25, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    2e751c8 View commit details
  3. build(docs): fix page time (#345)

    giladgd authored Sep 25, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    76cb79b View commit details
  4. docs: home page fixes (#346)

    giladgd authored Sep 25, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    578e710 View commit details

Commits on Sep 29, 2024

  1. feat: resolveModelFile method (#351)

    * feat: `resolveModelFile` method
    * feat: `hf:` URI support
    * fix: improve GGUF metadata read times
    * fix: hide internal type
    * docs: document the `hf:` URI
    giladgd authored Sep 29, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    4ee10a9 View commit details

Commits on Oct 5, 2024

  1. docs: improvements (#357)

    giladgd authored Oct 5, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    51eab61 View commit details

Commits on Oct 6, 2024

  1. feat(minor): reference common classes on the Llama instance (#360)

    giladgd authored Oct 6, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    8145c94 View commit details

Commits on Oct 29, 2024

  1. feat: chat session response prefix (#375)

    * feat: chat session response prefix
    * feat: improve context shift strategy
    * feat: use RAM and swap sizes in memory usage estimations
    * feat(`inspect gguf` command): print a single key flag
    * feat: faster building from source
    * fix: Electron crash with some models on macOS when not using Metal
    * fix: adapt to `llama.cpp` breaking changes
    * fix: improve CPU compatibility score
    giladgd authored Oct 29, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    ea12dc5 View commit details

Commits on Oct 31, 2024

  1. chore: update modules (#376)

    giladgd authored Oct 31, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    ff02ebd View commit details
  2. fix: build warning on macOS (#377)

    giladgd authored Oct 31, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    6405ee9 View commit details

Commits on Nov 27, 2024

  1. feat: Llama 3.2 3B function calling support (#386)

    * feat: Llama 3.2 3B function calling support
    * feat: use `llama.cpp` backend registry for GPUs instead of custom implementations
    * feat(`getLlama`): `build: "try"` option
    * feat(`init` command): `--model` flag
    * fix: improve binary compatibility testing on Electron apps
    * fix: too many abort signal listeners
    * fix: log level of some lower level logs
    * fix: context window missing response during generation on specific extreme conditions
    * fix: adapt to breaking `llama.cpp` changes
    * fix: automatically resolve `compiler is out of heap space` CUDA build error
    * chore: update bug report template
    * docs: separate open source and proprietary sections in the awesome list
    * docs(troubleshooting): Electron build error on Windows
    * docs(Electron): GitHub Actions template for cross-compilation
    giladgd authored Nov 27, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    97abbca View commit details

Commits on Nov 28, 2024

  1. build: fix CI (#389)

    giladgd authored Nov 28, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    bc6cfe3 View commit details

Commits on Dec 1, 2024

  1. feat: JSON Schema grammar enhancements (#388)

    * feat(JSON Schema grammar): `prefixItems`, `minItems`, `maxItems` support
    * feat(JSON Schema grammar): improve inferred types
    * feat(JSON Schema grammar): object `additionalProperties`, `minProperties`, `maxProperties`
    * feat(JSON Schema grammar): string `minLength`, `maxLength`, `format`
    * feat(function calling): params `description` support
    * feat(function calling): document JSON Schema type properties on Functionary chat function types
    * docs: how to reduce hallucinations when using JSON schema grammar
    * fix: bugs
    * chore: update dependencies
    giladgd authored Dec 1, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    4d387de View commit details

Commits on Dec 7, 2024

  1. fix: align embedding input with WPM vocabulary type models (#393)

    giladgd authored Dec 7, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    28c7984 View commit details

Commits on Dec 8, 2024

  1. docs: choosing an embedding model (#396)

    giladgd authored Dec 8, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    6a54163 View commit details
Loading