build(deps): bump @qvac/sdk from 0.14.0 to 0.15.0

[dependabot]

Bumps @qvac/sdk from 0.14.0 to 0.15.0.

Release notes

Sourced from @​qvac/sdk's releases.

QVAC Embed Addon v0.15.0

Added

Multi-GPU pipeline parallelism via split-mode config

• New split-mode ('none' | 'layer' | 'row') and tensor-split config options enable distributing an embedding model across multiple GPUs via pipeline or tensor parallelism.
• When split-mode is 'layer' or 'row' and a GPU backend is available, the --device flag is omitted so llama.cpp distributes layers/rows across all available GPUs rather than pinning to a single device.
• When no GPU backend is available the addon falls back to CPU and silently drops split-mode, tensor-split, and main-gpu.
• main_gpu underscore variant is now accepted alongside main-gpu; providing both simultaneously throws InvalidArgument.
• split_mode underscore variant is accepted alongside split-mode; providing both simultaneously throws InvalidArgument.

QVAC SDK v0.15.0

📦 NPM: https://www.npmjs.com/package/@​qvac/sdk/v/0.15.0

QVAC SDK 0.15.0 introduces single-job batch completion for running many prompts through one loaded model, adds LavaSR speech enhancement and denoising to the TTS pipeline, and extends Chatterbox TTS to Japanese and Chinese. It also gives multimodal models explicit GPU/CPU control over the vision encoder and ships stability fixes for Android worklets, worker RPC teardown, registry caching, and symlinked installs.

New APIs

Single-Job Batch Completion

batchCompletion runs many prompts through a single loaded model in one job, streaming per-prompt deltas and returning ordered results. Each prompt can carry its own history, generation parameters, and optional per-prompt tools or MCP-sourced tools.

import {
  batchCompletion,
  loadModel,
  LLAMA_3_2_1B_INST_Q4_0,
} from "@qvac/sdk";
const modelId = await loadModel({
modelSrc: LLAMA_3_2_1B_INST_Q4_0,
modelType: "llm",
modelConfig: { ctx_size: 4096, parallel: 4 },
});
const run = batchCompletion({
modelId,
prompts: [
{
id: "a",
history: [{ role: "user", content: "Reply with only APPLE." }],
generationParams: { temp: 0, predict: 16 },
},
{
id: "b",
history: [{ role: "user", content: "What's the weather in Paris?" }],
tools: [getWeatherTool], // optional per-prompt tools
generationParams: { temp: 0, predict: 64 },
</tr></table>

... (truncated)

Changelog

Sourced from @​qvac/sdk's changelog.

[0.15.0]

📦 NPM: https://www.npmjs.com/package/@​qvac/sdk/v/0.15.0

QVAC SDK 0.15.0 introduces single-job batch completion for running many prompts through one loaded model, adds LavaSR speech enhancement and denoising to the TTS pipeline, and extends Chatterbox TTS to Japanese and Chinese. It also gives multimodal models explicit GPU/CPU control over the vision encoder and ships stability fixes for Android worklets, worker RPC teardown, registry caching, and symlinked installs.

New APIs

Single-Job Batch Completion

batchCompletion runs many prompts through a single loaded model in one job, streaming per-prompt deltas and returning ordered results. Each prompt can carry its own history, generation parameters, and optional per-prompt tools or MCP-sourced tools.

import { batchCompletion, loadModel, LLAMA_3_2_1B_INST_Q4_0 } from '@qvac/sdk'
const modelId = await loadModel({
modelSrc: LLAMA_3_2_1B_INST_Q4_0,
modelType: 'llm',
modelConfig: { ctx_size: 4096, parallel: 4 }
})
const run = batchCompletion({
modelId,
prompts: [
{
id: 'a',
history: [{ role: 'user', content: 'Reply with only APPLE.' }],
generationParams: { temp: 0, predict: 16 }
},
{
id: 'b',
history: [{ role: 'user', content: "What's the weather in Paris?" }],
tools: [getWeatherTool], // optional per-prompt tools
generationParams: { temp: 0, predict: 64 }
}
]
})
for await (const { id, event } of run.events) {
if (event.type === 'contentDelta') process.stdout.write([${id}] ${event.text})
}
const results = await run.results // ordered, all-or-nothing on stream-level failure
const stats = await run.stats // batch-level CompletionStats | undefined

GPU Placement for Multimodal Vision Encoders

Multimodal LLMs can now force the vision encoder (mmproj) onto the GPU or CPU explicitly via the mmproj-use-gpu config key. Omit it to keep the previous per-device-class auto-selection.

... (truncated)

Commits

• 1eab8dd QVAC-21451 chore: release @​qvac/sdk 0.15.0 (changelog + notices + docs) (#3186)
• 59d6dff chore[notask]: reformat SDK files (#3200)
• f26fc73 QVAC-21909 fix: map bare-rpc channel-closed errors to worker error classes (#...
• dc83d1a QVAC-21914 chore: adopt fabric 9341.1.6 consumer releases in SDK addon depend...
• 61de1fa QVAC-21985 feat[api]: expose llm-llamacpp mmproj-use-gpu config key (#3170)
• e7edbd7 test: add BatchCompletionExecutor to electron e2e consumer (#3154)
• 3be15e6 QVAC-13376 test[skiplog]: add e2e coverage for custom SDK plugin bundling (#3...
• ed3ba4c chore: bump SDK addon dependency ranges (#3150)
• 12e2f6f chore: Bump parakeet to 0.9.0 (#3122)
• 626a56e QVAC-21336 feat[api|mod]: add chatterbox japanese and chinese asset support (...
• 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 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)