1.14.2

Update to latest upstream llama.cpp source code:

• Fix support for llama-3.1, phi 3 and SmolLM

Full Changelog: 1.14.0...1.14.2

1.14.0

What's Changed

• save ETag metadata, add allowOffline option in #90
• Added experimental support for encoder-decoder architecture #91

Full Changelog: 1.13.0...1.14.0

1.13.0

What's Changed

• Update README.md by @flatsiedatsie in #78
• sync with upstream llama.cpp source code (+gemma2 support) by @ngxson in #81
• Fix exit() function crash if model is not loaded by @flatsiedatsie in #84
• Improve cache API by @ngxson in #80
• v1.13.0 by @ngxson in #85

New Contributors

• @flatsiedatsie made their first contribution in #78

Full Changelog: 1.12.1...1.13.0

1.12.1

What's Changed

• Sync with latest upstream source code + adapt to project structure change by @ngxson in #77

Full Changelog: 1.12.0...1.12.1

1.12.0

Important

In prior versions, if you initialize wllama with embeddings: true, you will still able to generate completions.

From v1.12.0, if you start wllama with embeddings: true, this will throws an error when you try to use createCompletion. You must add wllama.setOptions({ embeddings: false }) to turn of embeddings.

More details: This feature is introduced in ggerganov/llama.cpp#7477 , which allows models like GritLM to be used for both embeddings and text generation.

What's Changed

• Add wllama.setOptions by @ngxson in #73
• v1.12.0 by @ngxson in #74
• warn user if embeddings is incorrectly set by @ngxson in #75

Full Changelog: 1.11.0...1.12.0

1.11.0

What's Changed

• Internally generate the model URL array when the provided URL for loadModelFromUrl method is from a single shard of a model split with the gguf-split tool by @felladrin in #61
• Allow loading a model using relative path by @felladrin in #64
• Git ignore also .DS_Store which are created by MacOS Finder by @felladrin in #65
• v1.11.0 by @ngxson in #68

Full Changelog: 1.10.0...1.11.0

1.10.0

What's Changed

• loadModel() now also accepts Blob or File
• Added GGUFRemoteBlob that can stream Blob from a remote URL
• Added example for loading local gguf files
• Implement OPFS for cache

Note: Optionally, you can clear the CacheStorage used by previous version.

Pull requests:

• fix small typo in README by @ngxson in #51
• sync with latest llama.cpp source code by @ngxson in #59
• add Blob support + OPFS + load from local file(s) by @ngxson in #52
• v1.10.0 by @ngxson in #60

Full Changelog: 1.9.0...1.10.0

1.9.0

What's Changed

• Add support for EOT (end of turn) and stopTokens by @ngxson in #47
• Ability to get model metadata by @ngxson in #48
• Add custom logger by @ngxson in #49
• sync to upstream llama.cpp source code (+ release v1.9.0) by @ngxson in #50

Full Changelog: 1.8.1...1.9.0

1.8.1

What's Changed

• Introduce heapfs by @ngxson in #39

HeapFS allow us to save more memory while loading model. It also prevent doing memcpy, so loading model will be a bit faster.

• Make the config parameter of the loadModelFromUrl function optional by @felladrin in #32
• Remove prebuilt esm by @ngxson in #33
• Improve error handling on abort() by @ngxson in #34
• add tool for debugging memory by @ngxson in #37
• sync to upstream llama.cpp source code by @ngxson in #46

Full Changelog: 1.8.0...1.8.1

1.8.0

What's Changed

• Docs & demo address changed from ngxson.github.io to github.ngxson.com. This allows adding COOP/COEP headers (required to run multi-thread examples)
• Add download progress callback by @ngxson in #13
• Free buffer after uploaded to worker by @ngxson in #14
• Correct number of pthread pool size by @ngxson in #21
• Build docs on CI by @ngxson in #24
• fix OOM on iOS by @ngxson in #23
• Add abortSignal for createCompletion by @ngxson in #26
• Sync upstream llama.cpp source code by @ngxson in #27
• Better exception handling by @ngxson in #29

New Contributors

• @felladrin made their first contribution in #15

Full Changelog: https://github.com/ngxson/wllama/commits/1.8.0