@qvac/audiogen-ggml 0.10.0 → 0.11.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +63 -0
- package/README.md +83 -41
- package/audiogen.d.ts +4 -0
- package/benchmarks/RTF-BENCHMARKS.md +27 -33
- package/binding.js +2 -0
- package/examples/generate-with-backends.js +58 -0
- package/index.d.ts +14 -3
- package/index.js +24 -2
- package/lib/audio-format.js +137 -92
- package/lib/fit.d.ts +7 -1
- package/package.json +31 -16
package/CHANGELOG.md
CHANGED
|
@@ -7,6 +7,69 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
|
|
7
7
|
|
|
8
8
|
## [Unreleased]
|
|
9
9
|
|
|
10
|
+
## [0.11.0] - 2026-11-18
|
|
11
|
+
|
|
12
|
+
### Changed
|
|
13
|
+
|
|
14
|
+
- `@qvac/fabric` dependency bumped `^0.30.1` -> `^0.31.0`, which carries
|
|
15
|
+
`qvac-fabric` `11739.3.0#1` -> `11739.4.0`
|
|
16
|
+
([#5831](https://github.com/tetherto/qvac/pull/5831)): opt-in WebGPU builds,
|
|
17
|
+
mtmd-helper decode limits, Core ML FFN prefill for Qwen3.5 0.8B and 2B,
|
|
18
|
+
OpenCL fixes for device-side uploads, GROUP_NORM and long flash-attention
|
|
19
|
+
chunks, the XDNA fused decode and host-decode fallback, and TurboVec IVF
|
|
20
|
+
lists stored contiguously. The mobile dev and peer dependencies
|
|
21
|
+
`@qvac/fabric-android-arm64` / `@qvac/fabric-ios` move to `^0.31.0` with it.
|
|
22
|
+
- `@qvac/fabric` 0.31 adds fields to `common_params_speculative_draft` and the
|
|
23
|
+
`mtmd_helper_*` structs, so it is not ABI-compatible with 0.30.x. The RPC
|
|
24
|
+
protocol stays at 117. Every addon loaded in one process must resolve the
|
|
25
|
+
same `@qvac/fabric` minor. Mobile apps must move `@qvac/fabric` and
|
|
26
|
+
`@qvac/fabric-android-arm64` or `@qvac/fabric-ios` to `0.31.0` together.
|
|
27
|
+
- This package needed no code change for the new fabric.
|
|
28
|
+
- `qvac-lib-inference-addon-cpp` dependency floor raised `1.5.0` -> `1.7.0`
|
|
29
|
+
([#5812](https://github.com/tetherto/qvac/pull/5812)). 1.6.0 lets runtime
|
|
30
|
+
stat values be strings (`RuntimeStatValue`), and 1.7.0 adds
|
|
31
|
+
`JsAsyncTask::runOn` for running async work on an addon-owned executor.
|
|
32
|
+
Compile-time only; no API or runtime behaviour change for this package.
|
|
33
|
+
|
|
34
|
+
|
|
35
|
+
- Require `inference-addon-cpp` 1.6.0 for the shared runtime-stat value type
|
|
36
|
+
([#5812](https://github.com/tetherto/qvac/pull/5812)).
|
|
37
|
+
|
|
38
|
+
- Share the `@qvac/fabric` runtime and backend loader, retaining addon-local
|
|
39
|
+
speech engines built against its headers
|
|
40
|
+
([#5808](https://github.com/tetherto/qvac/pull/5808)).
|
|
41
|
+
|
|
42
|
+
- Build the bundled speech engine from the source published as
|
|
43
|
+
`speech-cpp` `2026-11-18` (`5e1e4d34`).
|
|
44
|
+
|
|
45
|
+
### Fixed
|
|
46
|
+
|
|
47
|
+
- `encode()` / `encodePcm()` release every bare-ffmpeg object they create for
|
|
48
|
+
compressed formats, including when an encode fails. Before this, each encode
|
|
49
|
+
kept the input PCM, the encoded output and the native FFmpeg state in memory
|
|
50
|
+
for the life of the process
|
|
51
|
+
([#5610](https://github.com/tetherto/qvac/pull/5610)).
|
|
52
|
+
|
|
53
|
+
## [0.10.1] - 2026-11-10
|
|
54
|
+
|
|
55
|
+
### Added
|
|
56
|
+
|
|
57
|
+
- ACE-Step `backend`, `lmBackend`, and `dumpStagesDir` controls, with matching
|
|
58
|
+
backend selection in `assessFit()` and opt-in WebGPU source builds.
|
|
59
|
+
- Apple Core ML VAE/conditioner support and MiniMax `coremlConditionerPath`
|
|
60
|
+
for generation and preflight; MiniMax Core ML memory projections remain `unknown`.
|
|
61
|
+
|
|
62
|
+
### Fixed
|
|
63
|
+
|
|
64
|
+
- ACE-Step `normalizeLoudness: false` returns the engine's raw output. The
|
|
65
|
+
addon rescaled every non-edit result to a 0.9 peak whatever the option said,
|
|
66
|
+
so the flag only switched off the engine's percentile pass. Samples the VAE
|
|
67
|
+
leaves outside `[-1, 1]` now saturate at int16 full scale on that path.
|
|
68
|
+
- ACE-Step lego stems keep their mix gain relative to the source; the same
|
|
69
|
+
rescale raised or lowered each stem to a 0.9 peak.
|
|
70
|
+
- Include independent LM device pools in `assessFit()` when the primary
|
|
71
|
+
pipeline runs on CPU, counting the host peak once.
|
|
72
|
+
|
|
10
73
|
## [0.10.0] - 2026-11-05
|
|
11
74
|
|
|
12
75
|
### Breaking
|
package/README.md
CHANGED
|
@@ -8,14 +8,11 @@ on desktop CPUs and GPUs and returns stereo 44.1 kHz audio.
|
|
|
8
8
|
|
|
9
9
|
## How it works
|
|
10
10
|
|
|
11
|
-
The C++
|
|
12
|
-
|
|
13
|
-
remain a stub. Only trusted default-branch
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
Non-PR runs build the triggering commit and reject inputs selecting another
|
|
17
|
-
repository or revision. PR events retain caller-selected PR-head checkouts.
|
|
18
|
-
See [C++ CI configuration](../../docs/ci/nx-ci-consolidation.md#optionsci-cheat-sheet).
|
|
11
|
+
The C++ tests run through the CI contract's `cpp:build` and `cpp:tests` targets
|
|
12
|
+
on the Ubuntu 22.04 CPU runner, with two build workers. Addon-level C++ tests
|
|
13
|
+
remain a stub. Only trusted default-branch runs save the shared vcpkg cache;
|
|
14
|
+
`cache-warm.yml` warms it on pushes that touch cache inputs, every 2 days, and
|
|
15
|
+
on dispatch. See [the package CI contract](../../docs/ci/workflow-standard.md).
|
|
19
16
|
|
|
20
17
|
Under the hood the model runs a small pipeline, and the addon just drives it and
|
|
21
18
|
hands you the audio:
|
|
@@ -92,27 +89,18 @@ dependency, pinned to the exact `@qvac/audiogen-ggml` version:
|
|
|
92
89
|
}
|
|
93
90
|
```
|
|
94
91
|
|
|
95
|
-
The
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
On x64 a CUDA build's module targets **compute capability 7.5 and newer**, with
|
|
108
|
-
native code for Turing (7.5 — RTX 20xx, GTX 16xx, T4), Ampere (8.0, 8.6), Ada
|
|
109
|
-
(8.9), Hopper (9.0), and Blackwell (12.0, 12.1). Anything newer JIT-compiles
|
|
110
|
-
from the bundled 8.0 PTX on first use, a one-off compile the driver caches. On
|
|
111
|
-
linux-arm64 the native set is Jetson Orin (8.7), Grace-Hopper (9.0), and
|
|
112
|
-
GB10 / DGX Spark (12.1), with discrete Ampere+ cards and newer parts covered
|
|
113
|
-
through the bundled 8.0 PTX. Volta and Pascal fall outside CUDA 13's support
|
|
114
|
-
entirely, so they have no code path here: the backend skips such devices at
|
|
115
|
-
registration and the addon falls back to Vulkan or CPU.
|
|
92
|
+
The ggml runtime is the shared `@qvac/fabric` prebuild, a dependency of this
|
|
93
|
+
package: the addon links it dynamically, ships no ggml of its own, and shares
|
|
94
|
+
one runtime in memory with every other fabric addon in the process. The
|
|
95
|
+
runtime ships Metal inside itself on macOS and iOS, and per-platform
|
|
96
|
+
runtime-loaded modules elsewhere (CPU variants, Vulkan, CUDA on linux-x64,
|
|
97
|
+
linux-arm64 and win32-x64, OpenCL on Android), so no backend is chosen at this
|
|
98
|
+
package's build time. Engaging CUDA needs the NVIDIA driver plus the CUDA 13
|
|
99
|
+
runtime libraries (cudart and cuBLAS) resolvable at load time; hosts that
|
|
100
|
+
cannot resolve them skip the module and fall back to Vulkan or CPU. The engine
|
|
101
|
+
prefers CUDA when both GPU backends are usable. The CUDA module's device
|
|
102
|
+
coverage (compute capability 7.5 and newer, Volta and Pascal excluded) is the
|
|
103
|
+
runtime's; see the `@qvac/fabric` README.
|
|
116
104
|
|
|
117
105
|
To build the native addon from source in a repository checkout:
|
|
118
106
|
|
|
@@ -165,9 +153,54 @@ the engine time into `arMs`, `conditionMs`, `flowMs` and `vocoderMs`, and
|
|
|
165
153
|
the song ended on its own. See
|
|
166
154
|
[`examples/generate-music-minimax.js`](examples/generate-music-minimax.js).
|
|
167
155
|
|
|
156
|
+
### ACE-Step backend selection and diagnostics
|
|
157
|
+
|
|
158
|
+
`config.backend` selects the primary native backend by name or device name,
|
|
159
|
+
for example `cpu`, `MTL0`, `CUDA0`, or `WebGPU`. `config.lmBackend` selects
|
|
160
|
+
an independent LM backend. Empty or `auto` keeps native automatic placement
|
|
161
|
+
and the existing `useGPU`/`nGpuLayers` behavior. An explicit unavailable
|
|
162
|
+
backend fails instead of silently selecting another one. Use the same
|
|
163
|
+
`backend` and `lmBackend` values in `assessFit()` to project that placement.
|
|
164
|
+
The returned device rows include the independent LM pool even when the
|
|
165
|
+
primary backend is CPU; the host CPU remains the last row and appears once.
|
|
166
|
+
|
|
167
|
+
`config.dumpStagesDir` enables native intermediate tensor dumps in an existing
|
|
168
|
+
directory. It is disabled when omitted or empty. The directory is not created
|
|
169
|
+
by the addon. See
|
|
170
|
+
[`examples/generate-with-backends.js`](examples/generate-with-backends.js).
|
|
171
|
+
|
|
172
|
+
The addon has no GPU build options of its own: GPU backends come with the
|
|
173
|
+
`@qvac/fabric` runtime. To enable WebGPU, build Fabric with
|
|
174
|
+
`-D VCPKG_MANIFEST_FEATURES=webgpu` and link its platform package before
|
|
175
|
+
building this addon. The default published runtime excludes WebGPU.
|
|
176
|
+
Once a runtime that carries WebGPU is linked, `backendId: 5` maps to `webgpu`;
|
|
177
|
+
native WebGPU support is unmeasured and its automatic placement keeps the LM
|
|
178
|
+
and detokenizer on CPU. Independent backend selection does not override
|
|
179
|
+
native operation or model compatibility checks. JavaScript packages do not
|
|
180
|
+
include Hexagon.
|
|
181
|
+
|
|
182
|
+
### Apple Core ML sidecars
|
|
183
|
+
|
|
184
|
+
Apple builds enable the native Core ML sidecar support. An ACE-Step VAE
|
|
185
|
+
sidecar is discovered next to its GGUF: `vae-BF16.gguf` uses
|
|
186
|
+
`vae-decoder.mlmodelc` (the native resolver removes the quantization suffix). Absent
|
|
187
|
+
sidecars retain the native VAE route. Its existing native failure/fallback
|
|
188
|
+
policy is unchanged. ACE-Step preflight sizes the native ggml VAE route;
|
|
189
|
+
it does not include the additional Core ML sidecar allocations.
|
|
190
|
+
|
|
191
|
+
MiniMax can instead receive `config.coremlConditionerPath`, the absolute path
|
|
192
|
+
to a compiled conditioner `.mlmodelc` on the inference host. Only its
|
|
193
|
+
conditioner convolution uses Core ML with CPU and ANE allowed; the native
|
|
194
|
+
layer mix and resampling remain on CPU, while the other stages retain
|
|
195
|
+
`device`/`useGPU` placement. This option alone does not enable the full Core ML
|
|
196
|
+
profile. An explicit invalid or unsupported conditioner fails to load.
|
|
197
|
+
Forward the same `coremlConditionerPath` to `assessFit()`; it returns
|
|
198
|
+
`{ status: 'unknown', devices: [], stats: {} }` because Core ML resident
|
|
199
|
+
memory cannot be projected.
|
|
200
|
+
|
|
168
201
|
### MiniMax full Core ML on macOS
|
|
169
202
|
|
|
170
|
-
On macOS 15+,
|
|
203
|
+
On macOS 15+, the addon-local audiogen engine includes the full Core ML runtime. Use
|
|
171
204
|
the original F16 GGUF pair and its matching compiled profile:
|
|
172
205
|
|
|
173
206
|
```js
|
|
@@ -192,7 +225,9 @@ must accommodate the prompt and generation; no request is truncated to fit it.
|
|
|
192
225
|
The programs stay resident between generations and are released on unload.
|
|
193
226
|
Core ML returns `backendId: 99` (`other`); native-only `backendDevice` and
|
|
194
227
|
`gpuFallbackReason` are omitted. Memory preflight returns
|
|
195
|
-
`
|
|
228
|
+
`{ status: 'unknown', devices: [], stats: {} }` for this route. The full
|
|
229
|
+
Core ML route remains experimental; exposing its controls does not establish
|
|
230
|
+
audio parity or a performance improvement for a profile.
|
|
196
231
|
|
|
197
232
|
CPU/ANE initial-logit parity against the native reference is still under
|
|
198
233
|
validation; the measured device policies are not a claim of identical sampled
|
|
@@ -663,8 +698,11 @@ runnable end-to-end script (`npm run example`).
|
|
|
663
698
|
| `inferenceSteps` / `shift` | Advanced; leave unset to auto-tune per DiT. `run()` can override both per call. |
|
|
664
699
|
| `cfgScale` | Default MiniMax flow guidance scale; `0` uses the model default. |
|
|
665
700
|
| `nGpuLayers` | GPU layers to offload when `useGPU` is set (99 = all). |
|
|
701
|
+
| `backend`, `lmBackend` | ACE-Step primary and independent LM backend names; empty/auto preserves native selection. |
|
|
702
|
+
| `dumpStagesDir` | ACE-Step existing directory for intermediate tensor dumps; omitted/empty disables dumps. |
|
|
703
|
+
| `coremlConditionerPath` | MiniMax compiled conditioner `.mlmodelc`; leaves other stages on the selected native device. |
|
|
666
704
|
| `threads` | CPU thread count (0 / unset = hardware default). |
|
|
667
|
-
| `backendsDir` | Advanced; directory scanned, as given, for dlopen'd ggml backend modules. Unset
|
|
705
|
+
| `backendsDir` | Advanced; directory scanned, as given, for dlopen'd ggml backend modules. Unset uses the directory the `@qvac/fabric` runtime loads its own backends from (its platform package, or next to the runtime in a `bare-link`ed app). |
|
|
668
706
|
|
|
669
707
|
`logger` — an optional object implementing `error`/`warn`/`info`/`debug`,
|
|
670
708
|
wrapped by a level-gated `QvacLogger`.
|
|
@@ -689,7 +727,7 @@ wrapped by a level-gated `QvacLogger`.
|
|
|
689
727
|
| `lmPhase1` | Allow the LM to infer missing metadata before generating semantic codes. |
|
|
690
728
|
| `simpleMode` | Expand the caption query into a full request (caption, lyrics, unset metadata) before synthesis. |
|
|
691
729
|
| `rewriteQuery` | LM FORMAT pass: rewrite the caption into a detailed description, preserving the lyric content. Requires real `lyrics` and `taskType: 'text2music'`; mutually exclusive with `simpleMode`. |
|
|
692
|
-
| `normalizeLoudness` | Percentile loudness normalization of generated audio (default `true`);
|
|
730
|
+
| `normalizeLoudness` | Percentile loudness normalization of generated audio, then a 0.9 peak (default `true`); `false` returns the raw engine output. Edits and lego stems are never normalized. |
|
|
693
731
|
| `generateLrc` | Synchronized lyric timestamps: `stats.lrc` (LRC text) + `stats.lyricsScore`. Requires lyrics and `taskType: 'text2music'`. |
|
|
694
732
|
| `computeQualityScore` | Teacher-forced LM quality score of the generated codes; `stats.qualityScore` in `[0, 1]`. Requires `taskType: 'text2music'`. |
|
|
695
733
|
| `dcwEnabled` / `dcwScaler` / `dcwHighScaler` | Haar DCW correction controls. |
|
|
@@ -799,6 +837,8 @@ and `vaePath` name them individually and win over it.
|
|
|
799
837
|
| `withSourceAudio` | Projects the extra VAE-encoder phase a cover or reference request loads. |
|
|
800
838
|
| `keepStages` | `-1` mirrors the engine, `0` forces the staged projection, `1` all-resident. |
|
|
801
839
|
| `gpuLayers` | Greater than 0 requests the GPU stack, with the fallbacks a real load applies. |
|
|
840
|
+
| `backend`, `lmBackend` | ACE-Step placement selectors, as the generation config takes them. |
|
|
841
|
+
| `coremlConditionerPath` | MiniMax conditioner path; projects as `unknown` with no device rows. |
|
|
802
842
|
| `threads`, `backendsDir` | As the load takes them. |
|
|
803
843
|
| `marginBytes` | Free memory that must remain for the projection to count as fitting. Defaults to 256 MiB. |
|
|
804
844
|
|
|
@@ -875,14 +915,12 @@ dispatches to the corresponding `audiogen-cpp` engine.
|
|
|
875
915
|
- `addon/src/addon/AddonJs.hpp` — `createInstance` / `activate` / `runJob`.
|
|
876
916
|
- `addon/src/model-interface/acestep/` — `AcestepModel`, wrapping the engine.
|
|
877
917
|
- `addon/src/model-interface/minimax/` — desktop-only `MinimaxModel`.
|
|
878
|
-
-
|
|
879
|
-
|
|
880
|
-
|
|
881
|
-
|
|
882
|
-
|
|
883
|
-
|
|
884
|
-
them keeps one copy of each: use releases that record the same
|
|
885
|
-
`ggml-speech`.
|
|
918
|
+
- Speech engines are compiled into each addon from the checksum-pinned source in [`speech-source.json`](../../cmake/qvac-addon/speech-source.json), using only the headers shipped by `@qvac/fabric`. No speech or ggml vcpkg port is built.
|
|
919
|
+
- The ggml runtime is the shared `@qvac/fabric` prebuild: the addon links it
|
|
920
|
+
dynamically (`DT_NEEDED qvac__fabric-<host>@0.bare`) and ships no ggml of
|
|
921
|
+
its own. The speech revision and checksum live in
|
|
922
|
+
[speech-source.json](../../cmake/qvac-addon/speech-source.json). See
|
|
923
|
+
[`packages/fabric/INTEGRATION.md`](../fabric/INTEGRATION.md).
|
|
886
924
|
|
|
887
925
|
## Fuzzing
|
|
888
926
|
|
|
@@ -950,3 +988,7 @@ version bump.
|
|
|
950
988
|
|
|
951
989
|
Apache-2.0. ACE-Step model weights belong to ACE Studio and StepFun.
|
|
952
990
|
MiniMax-Music3 weights are governed by the MiniMax-Music3 Community License.
|
|
991
|
+
|
|
992
|
+
Shared ggml logging belongs to Fabric. Speech initialization preserves its
|
|
993
|
+
callback; Whisper and Parakeet retain their engine-local log forwarding.
|
|
994
|
+
Explicit `backendsDir` overrides remain supported; an unset value uses Fabric.
|
package/audiogen.d.ts
CHANGED
|
@@ -11,6 +11,10 @@ export interface AudioGenConfigurationParams {
|
|
|
11
11
|
useGPU?: boolean;
|
|
12
12
|
/** MiniMax compute device ('cpu' | 'gpu' | 'auto'); overrides useGPU. */
|
|
13
13
|
device?: string;
|
|
14
|
+
backend?: string;
|
|
15
|
+
lmBackend?: string;
|
|
16
|
+
dumpStagesDir?: string;
|
|
17
|
+
coremlConditionerPath?: string;
|
|
14
18
|
coremlProfileDir?: string;
|
|
15
19
|
coremlComputeUnits?: string;
|
|
16
20
|
nGpuLayers?: number;
|
|
@@ -153,40 +153,34 @@ The matrix runner additionally honours `MATRIX_JSON` (the sweep) and
|
|
|
153
153
|
|
|
154
154
|
## Running in CI
|
|
155
155
|
|
|
156
|
-
|
|
157
|
-
|
|
158
|
-
|
|
159
|
-
|
|
160
|
-
`
|
|
161
|
-
|
|
162
|
-
|
|
163
|
-
|
|
164
|
-
`
|
|
165
|
-
|
|
166
|
-
|
|
167
|
-
|
|
168
|
-
|
|
169
|
-
|
|
170
|
-
|
|
171
|
-
|
|
172
|
-
|
|
173
|
-
`
|
|
156
|
+
audiogen is on the package CI contract, so the benchmarks run through
|
|
157
|
+
`benchmarks.yml`, dispatched with `-f packages=audiogen-ggml`.
|
|
158
|
+
|
|
159
|
+
**Desktop** is the `benchmark` target, one job per configuration in
|
|
160
|
+
`project.json`. Each configuration names a set in `ci/benchmark-matrix.json`
|
|
161
|
+
with `--matrix`: every runner sweeps the three
|
|
162
|
+
variants on CPU, and GPU-capable runners sweep them again on the platform backend
|
|
163
|
+
(Vulkan on linux/win32, Metal on darwin). Artifacts:
|
|
164
|
+
`audiogen-ggml-benchmark-<configuration>`. A job fails when the matrix runner
|
|
165
|
+
fails or writes no result.
|
|
166
|
+
|
|
167
|
+
**Mobile** runs when the dispatch sets `run_mobile`, on the chosen platform and
|
|
168
|
+
devices. The dispatch's `args` input picks the one matrix row the run measures,
|
|
169
|
+
as `key=value` words (`dit_variant`, `use_gpu`, `warmup`, `runs`, `duration`), for
|
|
170
|
+
example `args=dit_variant=sft use_gpu=true`; `ci/prepare-mobile.mjs` turns it into
|
|
171
|
+
the device environment and runs only the perf tests. The numbers leave the device
|
|
172
|
+
inside `[PERF_REPORT_START]` log markers, which the shared extractor scrapes.
|
|
173
|
+
Artifacts: `audiogen-ggml-perf-mobile-<platform>-<run number>`.
|
|
174
|
+
|
|
175
|
+
The `benchmark` target's `report` configuration then runs
|
|
176
|
+
`ci/benchmark-report.sh` over every result of the run and renders the findings
|
|
177
|
+
table onto the run summary.
|
|
178
|
+
|
|
179
|
+
`benchmarks.yml`'s `perf-report` job is the weekly cross-addon report. It measures
|
|
180
|
+
nothing itself: it re-aggregates the artifacts of the last six `Benchmarks` runs
|
|
181
|
+
into `reports/audiogen-ggml-performance.md`, which lands in that run's summary
|
|
174
182
|
alongside the other addons. ACE-Step is therefore only as fresh as the last
|
|
175
|
-
sweep
|
|
176
|
-
|
|
177
|
-
**Desktop** — `integration-test-audiogen-ggml.yml` with
|
|
178
|
-
`run_rtf_benchmarks: true`. Every runner sweeps the three variants on CPU;
|
|
179
|
-
GPU-capable runners sweep them again on the platform backend (Vulkan on
|
|
180
|
-
linux/win32, Metal on darwin). Artifacts: `rtf-results-audiogen-ggml-*`.
|
|
181
|
-
|
|
182
|
-
**Mobile** — `integration-mobile-test-audiogen-ggml.yml` with
|
|
183
|
-
`run_rtf_benchmarks: true`. One AWS Device Farm row per variant/provider on
|
|
184
|
-
Android and iOS, since each row downloads its variant's GGUFs on-device. The
|
|
185
|
-
numbers leave the device inside `[PERF_REPORT_START]` log markers, which the
|
|
186
|
-
shared extractor scrapes. Artifacts: `perf-report-audiogen-ggml-*`.
|
|
187
|
-
|
|
188
|
-
Both lanes are `continue-on-error`, so a configuration that OOMs or overruns
|
|
189
|
-
shows up as a missing row rather than a failed sweep.
|
|
183
|
+
sweep; nothing dispatches one on a schedule.
|
|
190
184
|
|
|
191
185
|
## How the findings table is built
|
|
192
186
|
|
package/binding.js
CHANGED
|
@@ -0,0 +1,58 @@
|
|
|
1
|
+
'use strict'
|
|
2
|
+
|
|
3
|
+
const fs = require('bare-fs')
|
|
4
|
+
const proc = require('bare-process')
|
|
5
|
+
const { AudioGen, assessFit } = require('@qvac/audiogen-ggml')
|
|
6
|
+
|
|
7
|
+
async function collectAudio(response) {
|
|
8
|
+
const chunks = []
|
|
9
|
+
let sampleRate = 0
|
|
10
|
+
let channels = 0
|
|
11
|
+
for await (const chunk of response.iterate()) {
|
|
12
|
+
if (!chunk.outputArray) continue
|
|
13
|
+
chunks.push(
|
|
14
|
+
Buffer.from(
|
|
15
|
+
chunk.outputArray.buffer,
|
|
16
|
+
chunk.outputArray.byteOffset,
|
|
17
|
+
chunk.outputArray.byteLength
|
|
18
|
+
)
|
|
19
|
+
)
|
|
20
|
+
sampleRate = chunk.sampleRate
|
|
21
|
+
channels = chunk.channels
|
|
22
|
+
}
|
|
23
|
+
return { pcm: Buffer.concat(chunks), sampleRate, channels, stats: await response.await() }
|
|
24
|
+
}
|
|
25
|
+
|
|
26
|
+
async function main() {
|
|
27
|
+
const [modelDir, backend, lmBackend, dumpStagesDir, outputPath] = proc.argv.slice(2)
|
|
28
|
+
if (!modelDir || !backend || !lmBackend || !dumpStagesDir || !outputPath) {
|
|
29
|
+
throw new Error(
|
|
30
|
+
'Usage: bare examples/generate-with-backends.js MODEL_DIR BACKEND LM_BACKEND EXISTING_DUMP_DIR OUTPUT.wav'
|
|
31
|
+
)
|
|
32
|
+
}
|
|
33
|
+
|
|
34
|
+
console.log(await assessFit({ modelsDir: modelDir, backend, lmBackend }))
|
|
35
|
+
const generator = new AudioGen({
|
|
36
|
+
files: { modelDir },
|
|
37
|
+
config: { backend, lmBackend, dumpStagesDir }
|
|
38
|
+
})
|
|
39
|
+
try {
|
|
40
|
+
await generator.load()
|
|
41
|
+
const response = await generator.run('A warm acoustic instrumental with gentle guitar', {
|
|
42
|
+
lyrics: '[Instrumental]',
|
|
43
|
+
duration: 6,
|
|
44
|
+
seed: 7
|
|
45
|
+
})
|
|
46
|
+
const { pcm, sampleRate, channels, stats } = await collectAudio(response)
|
|
47
|
+
const encoded = AudioGen.encode(pcm, 'wav', { sampleRate, channels })
|
|
48
|
+
fs.writeFileSync(outputPath, encoded.data)
|
|
49
|
+
console.log(stats)
|
|
50
|
+
} finally {
|
|
51
|
+
await generator.destroy()
|
|
52
|
+
}
|
|
53
|
+
}
|
|
54
|
+
|
|
55
|
+
main().catch((error) => {
|
|
56
|
+
console.error(error)
|
|
57
|
+
proc.exitCode = 1
|
|
58
|
+
})
|
package/index.d.ts
CHANGED
|
@@ -53,6 +53,14 @@ export interface AudioGenRuntimeConfig {
|
|
|
53
53
|
coremlProfileDir?: string;
|
|
54
54
|
/** MiniMax only: explicit Core ML device policy; requires coremlProfileDir. */
|
|
55
55
|
coremlComputeUnits?: AudiogenMinimaxCoreMLComputeUnits;
|
|
56
|
+
/** MiniMax only: compiled conditioner .mlmodelc; the remaining stages use device/useGPU. */
|
|
57
|
+
coremlConditionerPath?: string;
|
|
58
|
+
/** ACE-Step primary backend name or device name; empty/auto preserves native selection. */
|
|
59
|
+
backend?: string;
|
|
60
|
+
/** ACE-Step LM backend, selected independently from the primary backend. */
|
|
61
|
+
lmBackend?: string;
|
|
62
|
+
/** ACE-Step diagnostics: existing directory receiving native intermediate tensor dumps. */
|
|
63
|
+
dumpStagesDir?: string;
|
|
56
64
|
/** ACE-Step only: GPU layers to offload when `useGPU` is set (99 = all). */
|
|
57
65
|
nGpuLayers?: number;
|
|
58
66
|
/** 0 = engine auto-picks. */
|
|
@@ -136,8 +144,11 @@ export interface GenerateOptions {
|
|
|
136
144
|
/**
|
|
137
145
|
* Percentile loudness normalization on the generated audio (default true):
|
|
138
146
|
* the 99.999th-percentile sample scales to full scale and the tiny tail
|
|
139
|
-
* above it clips, matching the reference loudness
|
|
140
|
-
*
|
|
147
|
+
* above it clips, matching the reference loudness; the result is then
|
|
148
|
+
* scaled to a 0.9 peak for int16 headroom. Set false for the raw engine
|
|
149
|
+
* output at its own gain: samples the VAE leaves outside [-1, 1] saturate
|
|
150
|
+
* at int16 full scale. Audio edits and lego stems are never normalized, so
|
|
151
|
+
* a stem keeps its mix gain relative to the source.
|
|
141
152
|
*/
|
|
142
153
|
normalizeLoudness?: boolean;
|
|
143
154
|
/**
|
|
@@ -445,7 +456,7 @@ export interface UnderstandOptions {
|
|
|
445
456
|
lmTopK?: number;
|
|
446
457
|
}
|
|
447
458
|
/** Name of a backend `AudiogenStats.backendId` can resolve to. */
|
|
448
|
-
export type AudiogenBackendName = 'cpu' | 'metal' | 'cuda' | 'vulkan' | 'opencl' | 'other';
|
|
459
|
+
export type AudiogenBackendName = 'cpu' | 'metal' | 'cuda' | 'vulkan' | 'opencl' | 'webgpu' | 'other';
|
|
449
460
|
/** `AudiogenStats.backendId` codes, named. Codes match @qvac/tts-ggml. */
|
|
450
461
|
export declare const AUDIOGEN_BACKEND_NAMES: Readonly<Record<number, AudiogenBackendName>>;
|
|
451
462
|
/** `undefined` for an unset or unrecognised id, never a guessed name. */
|
package/index.js
CHANGED
|
@@ -48,6 +48,7 @@ exports.AUDIOGEN_BACKEND_NAMES = {
|
|
|
48
48
|
2: 'cuda',
|
|
49
49
|
3: 'vulkan',
|
|
50
50
|
4: 'opencl',
|
|
51
|
+
5: 'webgpu',
|
|
51
52
|
99: 'other'
|
|
52
53
|
};
|
|
53
54
|
/** `undefined` for an unset or unrecognised id, never a guessed name. */
|
|
@@ -365,8 +366,19 @@ function validateAcestepOptions(files, config) {
|
|
|
365
366
|
if (config.device !== undefined) {
|
|
366
367
|
throw invalidInput('ACE-Step does not accept device (use useGPU and nGpuLayers)');
|
|
367
368
|
}
|
|
368
|
-
|
|
369
|
-
|
|
369
|
+
validateRuntimeStrings(config);
|
|
370
|
+
if (config.coremlConditionerPath !== undefined ||
|
|
371
|
+
config.coremlProfileDir !== undefined ||
|
|
372
|
+
config.coremlComputeUnits !== undefined) {
|
|
373
|
+
throw invalidInput('coremlConditionerPath, coremlProfileDir and coremlComputeUnits are MiniMax-only options');
|
|
374
|
+
}
|
|
375
|
+
}
|
|
376
|
+
function validateRuntimeStrings(config) {
|
|
377
|
+
for (const key of ['backend', 'lmBackend', 'dumpStagesDir', 'coremlConditionerPath']) {
|
|
378
|
+
const value = config[key];
|
|
379
|
+
if (value !== undefined && (typeof value !== 'string' || value.includes('\0'))) {
|
|
380
|
+
throw invalidInput(`${key} must be a string without NUL characters`);
|
|
381
|
+
}
|
|
370
382
|
}
|
|
371
383
|
}
|
|
372
384
|
function validateMinimaxCoreMLConfig(config) {
|
|
@@ -384,6 +396,12 @@ function validateMinimaxCoreMLConfig(config) {
|
|
|
384
396
|
}
|
|
385
397
|
}
|
|
386
398
|
function validateMinimaxConfig(config) {
|
|
399
|
+
validateRuntimeStrings(config);
|
|
400
|
+
if (config.backend !== undefined ||
|
|
401
|
+
config.lmBackend !== undefined ||
|
|
402
|
+
config.dumpStagesDir !== undefined) {
|
|
403
|
+
throw invalidInput('MiniMax does not accept backend, lmBackend or dumpStagesDir');
|
|
404
|
+
}
|
|
387
405
|
validateMinimaxCoreMLConfig(config);
|
|
388
406
|
if (config.useGPU !== undefined && typeof config.useGPU !== 'boolean') {
|
|
389
407
|
throw invalidInput('useGPU must be a boolean');
|
|
@@ -610,6 +628,7 @@ class AudioGen {
|
|
|
610
628
|
threads,
|
|
611
629
|
useGPU: config.useGPU ?? false,
|
|
612
630
|
device: config.device,
|
|
631
|
+
coremlConditionerPath: config.coremlConditionerPath,
|
|
613
632
|
coremlProfileDir: config.coremlProfileDir,
|
|
614
633
|
coremlComputeUnits: config.coremlComputeUnits,
|
|
615
634
|
backendsDir
|
|
@@ -634,6 +653,9 @@ class AudioGen {
|
|
|
634
653
|
inferenceSteps: this._defaultInferenceSteps,
|
|
635
654
|
shift: requireAcestepShift(config.shift ?? 0),
|
|
636
655
|
useGPU: config.useGPU ?? false,
|
|
656
|
+
backend: config.backend,
|
|
657
|
+
lmBackend: config.lmBackend,
|
|
658
|
+
dumpStagesDir: config.dumpStagesDir,
|
|
637
659
|
nGpuLayers: requireFiniteNumber(config.nGpuLayers ?? 99, 'nGpuLayers', true),
|
|
638
660
|
threads,
|
|
639
661
|
backendsDir
|
package/lib/audio-format.js
CHANGED
|
@@ -230,7 +230,16 @@ function createWriteIO(ffmpeg) {
|
|
|
230
230
|
}
|
|
231
231
|
})
|
|
232
232
|
|
|
233
|
-
|
|
233
|
+
// OutputFormatContext takes the handle via transfer() before it can throw; track the new owner.
|
|
234
|
+
let owner = io
|
|
235
|
+
const transfer = io.transfer
|
|
236
|
+
io.transfer = () => (owner = transfer.call(io))
|
|
237
|
+
|
|
238
|
+
return {
|
|
239
|
+
io,
|
|
240
|
+
getData: () => Buffer.from(buf.subarray(0, size)),
|
|
241
|
+
destroy: () => owner.destroy()
|
|
242
|
+
}
|
|
234
243
|
}
|
|
235
244
|
|
|
236
245
|
// A read-only in-memory source for FFmpeg (feeds the decoder our WAV bytes).
|
|
@@ -307,109 +316,145 @@ function encodeWithFfmpeg(pcm, format, { sampleRate = 48000, channels = 2 } = {}
|
|
|
307
316
|
const outRate = spec.rate || sampleRate
|
|
308
317
|
const sampleFormat = C.sampleFormats[spec.sampleFormat]
|
|
309
318
|
|
|
310
|
-
//
|
|
311
|
-
|
|
312
|
-
|
|
313
|
-
|
|
314
|
-
|
|
315
|
-
|
|
319
|
+
// bare-ffmpeg handles have no GC finalizer: until destroyed, the IOContexts hold
|
|
320
|
+
// strong refs to their callbacks, which pin the input WAV and the output buffer.
|
|
321
|
+
let inFmt = null
|
|
322
|
+
let decoder = null
|
|
323
|
+
let cc = null
|
|
324
|
+
let sink = null
|
|
325
|
+
let ofc = null
|
|
326
|
+
let resampler = null
|
|
327
|
+
let fifo = null
|
|
328
|
+
let packet = null
|
|
329
|
+
let inPacket = null
|
|
330
|
+
let raw = null
|
|
331
|
+
|
|
332
|
+
try {
|
|
333
|
+
// --- decode side: wrap PCM as WAV so ffmpeg produces clean input frames ---
|
|
334
|
+
const wav = pcmToWav(pcm, { sampleRate, channels })
|
|
335
|
+
inFmt = new ffmpeg.InputFormatContext(createReadIO(ffmpeg, wav))
|
|
336
|
+
const inStream = inFmt.streams[0]
|
|
337
|
+
decoder = inStream.decoder()
|
|
338
|
+
decoder.open()
|
|
316
339
|
|
|
317
|
-
|
|
318
|
-
|
|
319
|
-
|
|
320
|
-
|
|
321
|
-
|
|
322
|
-
|
|
323
|
-
|
|
324
|
-
|
|
325
|
-
|
|
326
|
-
|
|
327
|
-
|
|
328
|
-
|
|
340
|
+
// --- encoder ---
|
|
341
|
+
const encoder = new ffmpeg.Encoder(spec.encoder)
|
|
342
|
+
cc = new ffmpeg.CodecContext(encoder)
|
|
343
|
+
cc.sampleRate = outRate
|
|
344
|
+
cc.sampleFormat = sampleFormat
|
|
345
|
+
cc.channelLayout = ffmpeg.ChannelLayout.from(layout)
|
|
346
|
+
cc.timeBase = new ffmpeg.Rational(1, outRate)
|
|
347
|
+
if (spec.experimental) {
|
|
348
|
+
try {
|
|
349
|
+
cc.setOption('strict', 'experimental')
|
|
350
|
+
} catch {
|
|
351
|
+
/* older bindings: option may already default to permissive */
|
|
352
|
+
}
|
|
329
353
|
}
|
|
330
|
-
|
|
331
|
-
|
|
332
|
-
const frameSize = cc.frameSize > 0 ? cc.frameSize : 4096
|
|
354
|
+
cc.open()
|
|
355
|
+
const frameSize = cc.frameSize > 0 ? cc.frameSize : 4096
|
|
333
356
|
|
|
334
|
-
|
|
335
|
-
|
|
336
|
-
|
|
337
|
-
|
|
338
|
-
|
|
339
|
-
|
|
357
|
+
// --- muxer (seekable in-memory) ---
|
|
358
|
+
sink = createWriteIO(ffmpeg)
|
|
359
|
+
ofc = new ffmpeg.OutputFormatContext(spec.container, sink.io)
|
|
360
|
+
const ostream = ofc.createStream()
|
|
361
|
+
ostream.codecParameters.fromContext(cc)
|
|
362
|
+
ofc.writeHeader()
|
|
340
363
|
|
|
341
|
-
|
|
342
|
-
|
|
343
|
-
|
|
344
|
-
|
|
345
|
-
|
|
346
|
-
|
|
347
|
-
|
|
348
|
-
|
|
349
|
-
|
|
350
|
-
|
|
351
|
-
|
|
352
|
-
|
|
364
|
+
// --- resample (input format/rate -> encoder format/rate) + FIFO framing ---
|
|
365
|
+
resampler = new ffmpeg.Resampler(
|
|
366
|
+
inStream.codecParameters.sampleRate,
|
|
367
|
+
inStream.codecParameters.channelLayout,
|
|
368
|
+
inStream.codecParameters.format,
|
|
369
|
+
outRate,
|
|
370
|
+
layout,
|
|
371
|
+
sampleFormat
|
|
372
|
+
)
|
|
373
|
+
fifo = new ffmpeg.AudioFIFO(sampleFormat, channels, frameSize)
|
|
374
|
+
packet = new ffmpeg.Packet()
|
|
375
|
+
let pts = 0
|
|
353
376
|
|
|
354
|
-
|
|
355
|
-
|
|
356
|
-
|
|
357
|
-
|
|
358
|
-
|
|
359
|
-
|
|
360
|
-
|
|
377
|
+
const emit = (frame) => {
|
|
378
|
+
cc.sendFrame(frame)
|
|
379
|
+
while (cc.receivePacket(packet)) {
|
|
380
|
+
packet.streamIndex = ostream.index
|
|
381
|
+
packet.rescaleTimestamps(cc.timeBase, ostream.timeBase)
|
|
382
|
+
ofc.writeFrame(packet)
|
|
383
|
+
packet.unref()
|
|
384
|
+
}
|
|
361
385
|
}
|
|
362
|
-
}
|
|
363
386
|
|
|
364
|
-
|
|
365
|
-
|
|
366
|
-
|
|
367
|
-
|
|
368
|
-
|
|
369
|
-
|
|
370
|
-
|
|
371
|
-
|
|
372
|
-
|
|
373
|
-
|
|
374
|
-
|
|
375
|
-
|
|
376
|
-
|
|
387
|
+
const drain = (flush) => {
|
|
388
|
+
while (fifo.size >= frameSize || (flush && fifo.size > 0)) {
|
|
389
|
+
const n = Math.min(frameSize, fifo.size)
|
|
390
|
+
const frame = new ffmpeg.Frame()
|
|
391
|
+
try {
|
|
392
|
+
frame.format = sampleFormat
|
|
393
|
+
frame.channelLayout = ffmpeg.ChannelLayout.from(layout)
|
|
394
|
+
frame.sampleRate = outRate
|
|
395
|
+
frame.nbSamples = n
|
|
396
|
+
frame.alloc()
|
|
397
|
+
fifo.read(frame, n)
|
|
398
|
+
frame.pts = pts
|
|
399
|
+
pts += n
|
|
400
|
+
emit(frame)
|
|
401
|
+
} finally {
|
|
402
|
+
frame.destroy()
|
|
403
|
+
}
|
|
404
|
+
}
|
|
377
405
|
}
|
|
378
|
-
}
|
|
379
406
|
|
|
380
|
-
|
|
381
|
-
|
|
382
|
-
|
|
383
|
-
|
|
384
|
-
|
|
385
|
-
|
|
386
|
-
|
|
387
|
-
|
|
388
|
-
|
|
389
|
-
|
|
390
|
-
|
|
391
|
-
|
|
392
|
-
|
|
407
|
+
const pushResampled = (rawFrame) => {
|
|
408
|
+
const out = new ffmpeg.Frame()
|
|
409
|
+
try {
|
|
410
|
+
out.channelLayout = ffmpeg.ChannelLayout.from(layout)
|
|
411
|
+
out.format = sampleFormat
|
|
412
|
+
out.sampleRate = outRate
|
|
413
|
+
const inSamples = rawFrame ? rawFrame.nbSamples : 1024
|
|
414
|
+
out.nbSamples =
|
|
415
|
+
Math.ceil((inSamples * outRate) / inStream.codecParameters.sampleRate) + 1024
|
|
416
|
+
const samples = new ffmpeg.Samples()
|
|
417
|
+
samples.fill(out)
|
|
418
|
+
const count = rawFrame ? resampler.convert(rawFrame, out) : resampler.flush(out)
|
|
419
|
+
if (count > 0) {
|
|
420
|
+
out.nbSamples = count
|
|
421
|
+
fifo.write(out)
|
|
422
|
+
}
|
|
423
|
+
return count
|
|
424
|
+
} finally {
|
|
425
|
+
out.destroy()
|
|
426
|
+
}
|
|
393
427
|
}
|
|
394
|
-
return count
|
|
395
|
-
}
|
|
396
428
|
|
|
397
|
-
|
|
398
|
-
|
|
399
|
-
|
|
400
|
-
|
|
401
|
-
|
|
402
|
-
|
|
403
|
-
|
|
404
|
-
|
|
405
|
-
|
|
406
|
-
|
|
407
|
-
|
|
408
|
-
|
|
409
|
-
|
|
410
|
-
|
|
429
|
+
inPacket = new ffmpeg.Packet()
|
|
430
|
+
raw = new ffmpeg.Frame()
|
|
431
|
+
while (inFmt.readFrame(inPacket)) {
|
|
432
|
+
decoder.sendPacket(inPacket)
|
|
433
|
+
while (decoder.receiveFrame(raw)) pushResampled(raw)
|
|
434
|
+
inPacket.unref()
|
|
435
|
+
drain(false)
|
|
436
|
+
}
|
|
437
|
+
while (pushResampled(null) > 0) {
|
|
438
|
+
/* flush the resampler's internal buffer */
|
|
439
|
+
}
|
|
440
|
+
drain(true)
|
|
441
|
+
emit(null) // flush the encoder
|
|
442
|
+
ofc.writeTrailer()
|
|
411
443
|
|
|
412
|
-
|
|
444
|
+
return sink.getData()
|
|
445
|
+
} finally {
|
|
446
|
+
raw?.destroy()
|
|
447
|
+
inPacket?.destroy()
|
|
448
|
+
packet?.destroy()
|
|
449
|
+
fifo?.destroy()
|
|
450
|
+
resampler?.destroy()
|
|
451
|
+
cc?.destroy()
|
|
452
|
+
decoder?.destroy()
|
|
453
|
+
ofc?.destroy()
|
|
454
|
+
// No-op once ofc owns the IO; releases it if OutputFormatContext was never created.
|
|
455
|
+
sink?.destroy()
|
|
456
|
+
inFmt?.destroy()
|
|
457
|
+
}
|
|
413
458
|
}
|
|
414
459
|
|
|
415
460
|
// Encode a single format. `pcm`/`wav` stay dependency-free; the rest go through
|
package/lib/fit.d.ts
CHANGED
|
@@ -19,6 +19,10 @@ export interface AudiogenFitRequest {
|
|
|
19
19
|
/** MiniMax synthesis GGUF; pairs with `lmPath`. */
|
|
20
20
|
synthPath?: string
|
|
21
21
|
|
|
22
|
+
/** ACE-Step primary backend name/device; empty/auto preserves native selection. */
|
|
23
|
+
backend?: string
|
|
24
|
+
/** ACE-Step LM backend, independent of the primary backend. */
|
|
25
|
+
lmBackend?: string
|
|
22
26
|
/** > 0 requests the GPU stack, with the fallbacks a real load applies. */
|
|
23
27
|
gpuLayers?: number
|
|
24
28
|
/**
|
|
@@ -26,7 +30,9 @@ export interface AudiogenFitRequest {
|
|
|
26
30
|
* > 0 projects `auto` (a GPU when one is usable) and anything else `cpu`.
|
|
27
31
|
*/
|
|
28
32
|
device?: 'cpu' | 'gpu' | 'auto'
|
|
29
|
-
/** MiniMax
|
|
33
|
+
/** MiniMax compiled conditioner. Core ML projection returns status unknown with no device rows. */
|
|
34
|
+
coremlConditionerPath?: string
|
|
35
|
+
/** MiniMax full Core ML profile. Projection returns status unknown with no device rows. */
|
|
30
36
|
coremlProfileDir?: string
|
|
31
37
|
coremlComputeUnits?: 'CPU_ONLY' | 'CPU_AND_GPU' | 'CPU_AND_NE' | 'ALL'
|
|
32
38
|
threads?: number
|
package/package.json
CHANGED
|
@@ -1,10 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@qvac/audiogen-ggml",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.11.0",
|
|
4
4
|
"description": "Audio generation (music) addon for qvac",
|
|
5
|
-
"qvac": {
|
|
6
|
-
"ggml-speech": "2026-10-27#1"
|
|
7
|
-
},
|
|
8
5
|
"engines": {
|
|
9
6
|
"bare": ">=1.19.0"
|
|
10
7
|
},
|
|
@@ -35,9 +32,7 @@
|
|
|
35
32
|
"scripts": {
|
|
36
33
|
"build": "npm run build:ts && npm run build:native",
|
|
37
34
|
"build:native": "bare-make generate -D BUILD_FUZZING=OFF && bare-make build && bare-make install && npm run link:platform",
|
|
38
|
-
"build:native:cuda": "bare-make generate -D ENABLE_CUDA=ON -D BUILD_FUZZING=OFF && bare-make build && bare-make install && npm run link:platform",
|
|
39
35
|
"link:platform": "node ../../scripts/ci/slice-platform-packages.mjs --link-local --workdir .",
|
|
40
|
-
"build:cuda": "npm run build:ts && npm run build:native:cuda",
|
|
41
36
|
"build:ts": "tsc -p tsconfig.build.json",
|
|
42
37
|
"build:pack": "npm run build:ts && mkdir -p dist && npm pack --pack-destination dist",
|
|
43
38
|
"example": "bare examples/generate-music.js \"Upbeat pop rock with driving electric guitars and a catchy hook\"",
|
|
@@ -113,7 +108,8 @@
|
|
|
113
108
|
"README.md",
|
|
114
109
|
"CHANGELOG.md",
|
|
115
110
|
"NOTICE",
|
|
116
|
-
"LICENSE"
|
|
111
|
+
"LICENSE",
|
|
112
|
+
"examples/generate-with-backends.js"
|
|
117
113
|
],
|
|
118
114
|
"license": "Apache-2.0",
|
|
119
115
|
"repository": {
|
|
@@ -145,7 +141,17 @@
|
|
|
145
141
|
"prettier-config-holepunch": "^2.0.0",
|
|
146
142
|
"typescript": "^6.0.3",
|
|
147
143
|
"typescript-eslint": "^8.63.0",
|
|
148
|
-
"cmake-npm": "^1.1.0"
|
|
144
|
+
"cmake-npm": "^1.1.0",
|
|
145
|
+
"bare": "^1.36.0",
|
|
146
|
+
"bare-runtime": "^1.36.0",
|
|
147
|
+
"bare-make": "^2.1.0",
|
|
148
|
+
"cmake-toolchains": "^2.1.0",
|
|
149
|
+
"cmake-runtime": "^4.1.1",
|
|
150
|
+
"llvm-runtime": "^23.1.0",
|
|
151
|
+
"nasm-runtime": "^3.2.0",
|
|
152
|
+
"ninja-runtime": "^1.13.1",
|
|
153
|
+
"@qvac/fabric-android-arm64": "^0.31.0",
|
|
154
|
+
"@qvac/fabric-ios": "^0.31.0"
|
|
149
155
|
},
|
|
150
156
|
"dependencies": {
|
|
151
157
|
"@qvac/error": "^0.1.1",
|
|
@@ -155,24 +161,33 @@
|
|
|
155
161
|
"bare-fs": "^4.5.6",
|
|
156
162
|
"bare-os": "^3.8.0",
|
|
157
163
|
"bare-path": "^3.0.0",
|
|
158
|
-
"bare-process": "^4.2.2"
|
|
164
|
+
"bare-process": "^4.2.2",
|
|
165
|
+
"@qvac/fabric": "^0.31.0"
|
|
159
166
|
},
|
|
160
167
|
"optionalDependencies": {
|
|
161
|
-
"@qvac/audiogen-ggml-linux-x64": "0.
|
|
162
|
-
"@qvac/audiogen-ggml-linux-arm64": "0.
|
|
163
|
-
"@qvac/audiogen-ggml-darwin-arm64": "0.
|
|
164
|
-
"@qvac/audiogen-ggml-darwin-x64": "0.
|
|
165
|
-
"@qvac/audiogen-ggml-win32-x64": "0.
|
|
168
|
+
"@qvac/audiogen-ggml-linux-x64": "0.11.0",
|
|
169
|
+
"@qvac/audiogen-ggml-linux-arm64": "0.11.0",
|
|
170
|
+
"@qvac/audiogen-ggml-darwin-arm64": "0.11.0",
|
|
171
|
+
"@qvac/audiogen-ggml-darwin-x64": "0.11.0",
|
|
172
|
+
"@qvac/audiogen-ggml-win32-x64": "0.11.0"
|
|
166
173
|
},
|
|
167
174
|
"overrides": {
|
|
168
175
|
"bare-module-lexer": "1.6.3"
|
|
169
176
|
},
|
|
170
177
|
"types": "index.d.ts",
|
|
171
178
|
"peerDependencies": {
|
|
172
|
-
"@qvac/
|
|
173
|
-
"@qvac/
|
|
179
|
+
"@qvac/fabric-android-arm64": "^0.31.0",
|
|
180
|
+
"@qvac/fabric-ios": "^0.31.0",
|
|
181
|
+
"@qvac/audiogen-ggml-android-arm64": "0.11.0",
|
|
182
|
+
"@qvac/audiogen-ggml-ios": "0.11.0"
|
|
174
183
|
},
|
|
175
184
|
"peerDependenciesMeta": {
|
|
185
|
+
"@qvac/fabric-android-arm64": {
|
|
186
|
+
"optional": true
|
|
187
|
+
},
|
|
188
|
+
"@qvac/fabric-ios": {
|
|
189
|
+
"optional": true
|
|
190
|
+
},
|
|
176
191
|
"@qvac/audiogen-ggml-android-arm64": {
|
|
177
192
|
"optional": true
|
|
178
193
|
},
|