mirror/LocalAI
1
0 Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-11-07 13:03:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

docs(text-to-audio): document qwen3-tts-cpp max_batch

Browse Source 
Signed-off-by: nexxtmobile.de <git@nexxtmobile.de>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
nexxtmobile.deandClaude Opus 5.5 committed 2026-10-25 12:55:18 +00:00
1 parent 0b7d0b40ed
commit 074bc84f0c
2 files changed
+17 -3
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

backend/go/qwen3-tts-cpp/README.md
+4 -3
View File
@@ -76,9 +76,10 @@ requests (time to the first PCM chunk): RTX 5060 Ti 0.02/0.36/0.70/1.04 s with
- Incremental synthesis (`TTSLive`, the realtime pipeline with
`streaming.tts: true`) requires `max_batch:1` and is rejected otherwise
(qwentts `docs/INCREMENTAL.md`).
- ROCm on gfx1201 (RDNA4) hangs the GPU in hipBLASLt for batched matmuls;
`env: {ROCBLAS_USE_HIPBLASLT: "0"}` in the model config routes them to
rocBLAS. CUDA needs no workaround.
- ROCm before 10.1 on gfx1201 (RDNA4) hangs the GPU in hipBLASLt for the
batched matmuls (fixed upstream by ROCm/rocm-libraries#8909; ROCm 10.1 runs
clean). On older stacks `env: {ROCBLAS_USE_HIPBLASLT: "0"}` in the model
config routes them to rocBLAS. CUDA needs no workaround.
Request precedence is: a request `voice`, then `tts.voice`, then
`tts.audio_path`. A saved profile supplies its private WAV and exact transcript