Fix CUDA OOM by mutually unloading Whisper and ChatTTS on 8GB GPU.

Release GPU memory before TTS/ASR switches, lower TTS token limits, and set PYTORCH_CUDA_ALLOC_CONF in PM2. Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-12 17:03:37 +08:00
parent 82f99c0b89
commit 0cce6cda7c
7 changed files with 169 additions and 40 deletions
@@ -13,3 +13,7 @@ OLLAMA_PORT=11434
 # WHISPER_MODEL_DIR=/opt/Trading_Studio/models/whisper
 # WHISPER_MODEL_SIZE=small
 # HF_ENDPOINT=https://hf-mirror.com
+
+# 8GB 显存 OOM 时可调低（合成按段切分）
+# TTS_MAX_CHARS_PER_CHUNK=150
+# TTS_MAX_NEW_TOKEN=768