[PR #270] [CLOSED] Bump node-llama-cpp from 3.0.0-beta.44 to 3.4.0 #306

New issue

Closed

opened 2026-03-03 13:53:58 +03:00 by kerem · 0 comments

kerem commented

2026-03-03 13:53:58 +03:00

Owner

📋 Pull Request Information

Original PR: https://github.com/jehna/humanify/pull/270
Author: @dependabot[bot]
Created: 1/8/2025
Status: ❌ Closed

Base: main ← Head: dependabot/npm_and_yarn/node-llama-cpp-3.4.0

📝 Commits (1)

833fdd3 Bump node-llama-cpp from 3.0.0-beta.44 to 3.4.0

📊 Changes

1 file changed (+438 additions, -265 deletions)

View changed files

📝 package-lock.json (+438 -265)

📄 Description

Bumps node-llama-cpp from 3.0.0-beta.44 to 3.4.0.

Release notes

Sourced from node-llama-cpp's releases.

v3.4.0

3.4.0 (2025-01-08)

Features

token prediction (speculative decoding) (#405) (632a7bf) (documentation: Token Prediction)

controlledEvaluate (#405) (632a7bf) (documentation: Low Level API)

evaluateWithMetadata (#405) (632a7bf) (documentation: Low Level API)

reranking (#405) (632a7bf) (documentation: Reranking Documents)

token confidence (#405) (632a7bf) (documentation: Low Level API)

experimentalChunkDocument (#405) (632a7bf)

build on arm64 using LLVM (#405) (632a7bf)

try compiling with LLVM on Windows x64 when available (#405) (632a7bf)

minor: dynamically load llama.cpp backends (#405) (632a7bf)

minor: more token values support in SpecialToken (#405) (632a7bf)

minor: improve memory usage estimation (#405) (632a7bf)

Bug Fixes

check for Rosetta usage on macOS x64 when using the inspect gpu command (#405) (632a7bf)

detect running under Rosetta on Apple Silicone and show an error message instead of crashing (#405) (632a7bf)

switch from "nextTick" to "nextCycle" for the default batch dispatcher (#405) (632a7bf)

remove deprecated CLS token (#405) (632a7bf)

pipe error logs in inspect gpu command (#405) (632a7bf)

Shipped with llama.cpp release b4435

To use the latest llama.cpp release available, run npx -n node-llama-cpp source download --release latest. (learn more)

v3.3.2

3.3.2 (2024-12-27)

Bug Fixes

embedding context deadlock (#402) (e2c5c3f)

Shipped with llama.cpp release b4291

To use the latest llama.cpp release available, run npx -n node-llama-cpp source download --release latest. (learn more)

... (truncated)

Commits

d1b4416 fix: reranking probabilities (#412)
5d07289 chore: update modules (#411)
632a7bf feat: token prediction (speculative decoding) (#405)
e2c5c3f fix: embedding context deadlock (#402)
6a54163 docs: choosing an embedding model (#396)
28c7984 fix: align embedding input with WPM vocabulary type models (#393)
4d387de feat: JSON Schema grammar enhancements (#388)
bc6cfe3 build: fix CI (#389)
97abbca feat: Llama 3.2 3B function calling support (#386)
6405ee9 fix: build warning on macOS (#377)
Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR
@dependabot recreate will recreate this PR, overwriting any edits that have been made to it
@dependabot merge will merge this PR after your CI passes on it
@dependabot squash and merge will squash and merge this PR after your CI passes on it
@dependabot cancel merge will cancel a previously requested merge and block automerging
@dependabot reopen will reopen this PR if it is closed
@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
@dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/jehna/humanify/pull/270 **Author:** [@dependabot[bot]](https://github.com/apps/dependabot) **Created:** 1/8/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `dependabot/npm_and_yarn/node-llama-cpp-3.4.0` --- ### 📝 Commits (1) - [`833fdd3`](https://github.com/jehna/humanify/commit/833fdd3656a08fc0924f5a48c6814e9e25accab4) Bump node-llama-cpp from 3.0.0-beta.44 to 3.4.0 ### 📊 Changes **1 file changed** (+438 additions, -265 deletions) <details> <summary>View changed files</summary> 📝 `package-lock.json` (+438 -265) </details> ### 📄 Description Bumps [node-llama-cpp](https://github.com/withcatai/node-llama-cpp) from 3.0.0-beta.44 to 3.4.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/withcatai/node-llama-cpp/releases">node-llama-cpp's releases</a>.</em></p> <blockquote> <h2>v3.4.0</h2> <h1><a href="https://github.com/withcatai/node-llama-cpp/compare/v3.3.2...v3.4.0">3.4.0</a> (2025-01-08)</h1> <h3>Features</h3> <ul> <li>token prediction (speculative decoding) (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>) (documentation: <a href="https://node-llama-cpp.withcat.ai/guide/token-prediction">Token Prediction</a>)</li> <li><code>controlledEvaluate</code> (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>) (documentation: <a href="https://node-llama-cpp.withcat.ai/guide/low-level-api#controlled-evaluation">Low Level API</a>)</li> <li><code>evaluateWithMetadata</code> (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>) (documentation: <a href="https://node-llama-cpp.withcat.ai/guide/low-level-api#evaluation-with-metadata">Low Level API</a>)</li> <li>reranking (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>) (documentation: <a href="https://node-llama-cpp.withcat.ai/guide/embedding#reranking">Reranking Documents</a>)</li> <li>token confidence (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>) (documentation: <a href="https://node-llama-cpp.withcat.ai/guide/low-level-api#controlled-evaluation">Low Level API</a>)</li> <li><code>experimentalChunkDocument</code> (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>)</li> <li>build on arm64 using LLVM (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>)</li> <li>try compiling with LLVM on Windows x64 when available (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>)</li> <li><strong>minor</strong>: dynamically load <code>llama.cpp</code> backends (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>)</li> <li><strong>minor</strong>: more token values support in <code>SpecialToken</code> (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>)</li> <li><strong>minor</strong>: improve memory usage estimation (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>)</li> </ul> <h3>Bug Fixes</h3> <ul> <li>check for Rosetta usage on macOS x64 when using the <code>inspect gpu</code> command (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>)</li> <li>detect running under Rosetta on Apple Silicone and show an error message instead of crashing (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>)</li> <li>switch from <code>"nextTick"</code> to <code>"nextCycle"</code> for the default batch dispatcher (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>)</li> <li>remove deprecated CLS token (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>)</li> <li>pipe error logs in <code>inspect gpu</code> command (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da">632a7bf</a>)</li> </ul> <hr /> <p>Shipped with <code>llama.cpp</code> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4435"><code>b4435</code></a></p> <blockquote> <p>To use the latest <code>llama.cpp</code> release available, run <code>npx -n node-llama-cpp source download --release latest</code>. (<a href="https://node-llama-cpp.withcat.ai/guide/building-from-source#download-new-release">learn more</a>)</p> </blockquote> <h2>v3.3.2</h2> <h2><a href="https://github.com/withcatai/node-llama-cpp/compare/v3.3.1...v3.3.2">3.3.2</a> (2024-12-27)</h2> <h3>Bug Fixes</h3> <ul> <li>embedding context deadlock (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/402">#402</a>) (<a href="https://github.com/withcatai/node-llama-cpp/commit/e2c5c3fe4f27df91bc0b99c1aa373622d1ee6488">e2c5c3f</a>)</li> </ul> <hr /> <p>Shipped with <code>llama.cpp</code> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4291"><code>b4291</code></a></p> <blockquote> <p>To use the latest <code>llama.cpp</code> release available, run <code>npx -n node-llama-cpp source download --release latest</code>. (<a href="https://node-llama-cpp.withcat.ai/guide/building-from-source#download-new-release">learn more</a>)</p> </blockquote>  </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/withcatai/node-llama-cpp/commit/d1b44161e90bb1fe4097c62e0f18b9bb2de8da8e"><code>d1b4416</code></a> fix: reranking probabilities (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/412">#412</a>)</li> <li><a href="https://github.com/withcatai/node-llama-cpp/commit/5d07289d132dc7937263aa0de1dc812cd93824cb"><code>5d07289</code></a> chore: update modules (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/411">#411</a>)</li> <li><a href="https://github.com/withcatai/node-llama-cpp/commit/632a7bf78fcee2ba1fa46865c5a2aea31db3d4da"><code>632a7bf</code></a> feat: token prediction (speculative decoding) (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/405">#405</a>)</li> <li><a href="https://github.com/withcatai/node-llama-cpp/commit/e2c5c3fe4f27df91bc0b99c1aa373622d1ee6488"><code>e2c5c3f</code></a> fix: embedding context deadlock (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/402">#402</a>)</li> <li><a href="https://github.com/withcatai/node-llama-cpp/commit/6a541636d6379daac9ff04f79f0a93009e7ada2b"><code>6a54163</code></a> docs: choosing an embedding model (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/396">#396</a>)</li> <li><a href="https://github.com/withcatai/node-llama-cpp/commit/28c7984e769884e76c0aafb3c0b0217d90849d03"><code>28c7984</code></a> fix: align embedding input with WPM vocabulary type models (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/393">#393</a>)</li> <li><a href="https://github.com/withcatai/node-llama-cpp/commit/4d387ded56aedf8f8b8a77509962d95f8b0d5ae8"><code>4d387de</code></a> feat: JSON Schema grammar enhancements (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/388">#388</a>)</li> <li><a href="https://github.com/withcatai/node-llama-cpp/commit/bc6cfe3dbc82f81bafb3b1fc91f69a5b4e316630"><code>bc6cfe3</code></a> build: fix CI (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/389">#389</a>)</li> <li><a href="https://github.com/withcatai/node-llama-cpp/commit/97abbca063f0ccf1b69607638d42f5ccc6ee1e2d"><code>97abbca</code></a> feat: Llama 3.2 3B function calling support (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/386">#386</a>)</li> <li><a href="https://github.com/withcatai/node-llama-cpp/commit/6405ee945e792651123189aae2612212095765b6"><code>6405ee9</code></a> fix: build warning on macOS (<a href="https://redirect.github.com/withcatai/node-llama-cpp/issues/377">#377</a>)</li> <li>Additional commits viewable in <a href="https://github.com/withcatai/node-llama-cpp/compare/v3.0.0-beta.44...v3.4.0">compare view</a></li> </ul> </details> <br /> [![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=node-llama-cpp&package-manager=npm_and_yarn&previous-version=3.0.0-beta.44&new-version=3.4.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>