[Config Refactor] Migrate 5 TTS models (VoxCPM2 / CosyVoice3 / MiMo Audio / Voxtral TTS / Fish Speech S2 Pro) to Pipeline + Deploy schema (#2958)

Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
This commit is contained in:
Yueqian LinandSYLAR authored and GitHub committed 2026-04-21 21:17:53 +08:00
1 parent c2578f7131
commit 3f504b45d2
47 files changed
+702 -844

No files matched your search

@@ -29,15 +29,12 @@ Features:
## Launch the Server
```bash
vllm-omni serve fishaudio/s2-pro \
--stage-configs-path vllm_omni/model_executor/stage_configs/fish_speech_s2_pro.yaml \
--omni \
--port 8091 \
--trust-remote-code \
--enforce-eager \
--gpu-memory-utilization 0.9
vllm serve fishaudio/s2-pro --omni --port 8091
```
The deploy config is auto-loaded from `vllm_omni/deploy/fish_qwen3_omni.yaml`
(the HF `model_type` on the fishaudio checkpoints is `fish_qwen3_omni`).
Or use the convenience script:
```bash
@@ -11,18 +11,13 @@ MODEL="${MODEL:-fishaudio/s2-pro}"
PORT="${PORT:-8091}"
GRADIO_PORT="${GRADIO_PORT:-7860}"
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
REPO_ROOT="$(cd "$SCRIPT_DIR/../../.." && pwd)"
echo "Starting Fish Speech S2 Pro server (port $PORT)..."
FLASHINFER_DISABLE_VERSION_CHECK=1 \
vllm-omni serve "$MODEL" \
--stage-configs-path "$REPO_ROOT/vllm_omni/model_executor/stage_configs/fish_speech_s2_pro.yaml" \
vllm serve "$MODEL" \
--omni \
--host 0.0.0.0 \
--port "$PORT" \
--gpu-memory-utilization 0.9 \
--trust-remote-code \
--enforce-eager \
--omni &
--port "$PORT" &
SERVER_PID=$!
cleanup() {
@@ -13,11 +13,7 @@ PORT="${PORT:-8091}"
echo "Starting Fish Speech S2 Pro server with model: $MODEL"
FLASHINFER_DISABLE_VERSION_CHECK=1 \
vllm-omni serve "$MODEL" \
--stage-configs-path vllm_omni/model_executor/stage_configs/fish_speech_s2_pro.yaml \
vllm serve "$MODEL" \
--omni \
--host 0.0.0.0 \
--port "$PORT" \
--gpu-memory-utilization 0.9 \
--trust-remote-code \
--enforce-eager \
--omni
--port "$PORT"