Windows: Fluid Intelligence fails when incompatible System32 libomp takes precedence
I maintainer di solito rispondono entro 1 giorno
@altic-dev ci sta già lavorando.
Dal 23/7/2026.
Valutazione
Questa issue non è ancora stata valutata.
Descrizione
Summary
FluidVoice Windows 0.0.5 could not load the Fluid Intelligence llama.cpp backend when an older libomp140.x86_64.dll was present in C:\Windows\System32.
Windows resolved that system DLL instead of FluidVoice's compatible bundled copy. This produced an entry-point error for __kmpc_dispatch_deinit and prevented both the CUDA and CPU llama backends from loading.
Placing FluidVoice's bundled libomp140.x86_64.dll beside fluidvoice.exe fixed the problem immediately.
Environment
- FluidVoice Windows 0.0.5 beta
- Windows 10 Pro x64, build 19045
- Intel Core i7-6700K
- NVIDIA GeForce RTX 2070, compute capability 7.5
- CUDA driver API reported by FluidVoice: 13.3
- llama runtime:
llama-b9870
Steps to reproduce
- Install FluidVoice Windows 0.0.5.
- Complete onboarding and download the local speech/Fluid Intelligence models and runtimes.
- Enable or invoke Fluid Intelligence.
- Restart FluidVoice.
- Observe the Windows entry-point error while loading:
%LOCALAPPDATA%\FluidVoice\Runtimes\llama-cpp\llama-b9870\cuda\ggml-base.dll
Error
fluidvoice.exe - Entry Point Not Found
The procedure entry point __kmpc_dispatch_deinit could not be located
in the dynamic link library:
%LOCALAPPDATA%\FluidVoice\Runtimes\llama-cpp\llama-b9870\cuda\ggml-base.dll
Relevant FluidVoice log output:
Fluid Intelligence backend candidate failed: accelerator=cuda,
error=failed to load ...\llama-b9870\cuda\llama.dll
Fluid Intelligence backend candidate failed: accelerator=cpu,
error=failed to load ...\llama-b9870\cpu\llama.dll
Fluid Intelligence startup warmup failed:
No llama.cpp backend could load Fluid-1.
Diagnosis
Two different OpenMP runtimes were present:
System copy selected by Windows
C:\Windows\System32\libomp140.x86_64.dll
Size: 1,664,912 bytes
SHA-256: E8A22979342BA8D5F34E3500AE9A5DB1C1833A77446AA969C296345570178E37
__kmpc_dispatch_deinit: missing
FluidVoice bundled copy
%LOCALAPPDATA%\FluidVoice\Runtimes\llama-cpp\llama-b9870\cpu\libomp140.x86_64.dll
Size: 661,856 bytes
SHA-256: 4A20C1E5C115C29771A12324513EB109BADAC72180F79481527AD79D996FFB33
__kmpc_dispatch_deinit: present
The bundled CPU and CUDA copies were identical. Loading llama.dll in a fresh process with the runtime directory selected succeeded, which further indicated a DLL search-order conflict inside the FluidVoice process rather than corrupt runtime files or GPU incompatibility.
Workaround
Copying FluidVoice's bundled OpenMP DLL to the application directory:
%LOCALAPPDATA%\FluidVoice\libomp140.x86_64.dll
and restarting FluidVoice resolved the issue without modifying System32.
After the workaround, FluidVoice reported:
Loaded Fluid Intelligence llama.cpp backend:
accelerator=cuda, gpu_layers=-1, backend_argmax=true
A subsequent enhancement completed successfully on CUDA in 475 ms.
Expected behavior
FluidVoice should load the OpenMP runtime bundled with its selected llama runtime, regardless of another libomp140.x86_64.dll in System32 or PATH.
Possible direction
Ensure the runtime directory is used for dependent-DLL resolution before loading llama.dll—for example, with an isolated DLL search path—or ship the compatible OpenMP dependency beside fluidvoice.exe.
- Lingua principale
- Swift
- Stelle
- 11.9k
- Fork
- 863
- Merge medio
- 1g 14h
- PR unite (30g)
- 28
Preparare l'ambiente
Questo progetto non fornisce container di sviluppo, Dockerfile né guida per i contributori, quindi l'ambiente è a tuo carico: parti dal suo README e consulta la nostra guida al primo contributo per i passaggi generali.
Come iniziare
- Leggi tutta la issue e poi la guida ai contributi del progetto.
- Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
- Fai un fork del repository e lavora su un branch.
- Apri una pull request che faccia riferimento al numero della issue.
Altre issue di altic-dev/FluidVoice
-
[BUG] File transcription skips audio chunks shorter than one secondForse già presa @sabbah13 l’ha presa oggi. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
altic-dev/FluidVoice#1161 ·
I maintainer di solito rispondono entro 1 giorno
-
feat: add Nix flake support for one-command installationForse già presa @levonk l’ha presa oggi. Aperta
Difficoltà 4/5 3-5 giorni Idoneità per principianti 35/100
altic-dev/FluidVoice#1159 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 3/5 1-2 giorni Idoneità per principianti 62/100
altic-dev/FluidVoice#1156 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 4/5 3-5 giorni Idoneità per principianti 50/100
altic-dev/FluidVoice#1155 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 4/5 3-5 giorni Idoneità per principianti 22/100
altic-dev/FluidVoice#1154 ·
I maintainer di solito rispondono entro 1 giorno
Tutte le issue di altic-dev/FluidVoice
Issue simili
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 75/100
I maintainer di solito rispondono entro 1 giorno
-
swift.md: `Date(myString, strategy: .iso8601)` example omits `try` — the initializer is throwingAperta
Difficoltà 1/5 Meno di un'ora Idoneità per principianti 88/100
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 62/100
githubnext/desktop-tools#25 ·
I maintainer di solito rispondono entro 1 giorno
-
core: RAC_LLM_OPTIONS_DEFAULT.min_p disagrees with the IDL's annotated defaultForse già presa Una pull request collegata a questa issue è aperta o già unita. Apertabug core p3
Difficoltà 2/5 1-3 ore Idoneità per principianti 70/100
RunanywhereAI/runanywhere-sdks#1083 ·
I maintainer di solito rispondono entro 5 giorni
-
bug/fix needs: triage
Difficoltà 2/5 1-3 ore Idoneità per principianti 70/100
capawesome-team/capacitor-firebase#1054 ·
I maintainer di solito rispondono entro 1 giorno