inference Semaphore
Shared semaphore that limits concurrent local AI inferences across all modules (LLAMA, Tesseract, Whisper). Configured via AI_LLAMA_ENGINE_MaxConcurrent (default 2).
Shared semaphore that limits concurrent local AI inferences across all modules (LLAMA, Tesseract, Whisper). Configured via AI_LLAMA_ENGINE_MaxConcurrent (default 2).