perf: cap torch threads per camera worker

Default TORCH_NUM_THREADS=1 so 14-20 workers do not each spawn a
28-thread BLAS pool.

config.py

@@ -40,6 +40,7 @@ class Config:
     enhance_hop_s: float = 0.2
     # SpeechBrain Delay-and-Sum (GCC-PHAT) on C920 stereo before enhance
     beamform_mode: str = "auto"  # auto | force | off
+    torch_num_threads: int = 1
     # misc
     publish_timeout_s: float = 60.0
     log_level: str = "INFO"
@@ -86,6 +87,7 @@ def load_config(env_path: Optional[Path] = None) -> Config:
         enhance_chunk_s=float(os.environ.get("ENHANCE_CHUNK_S", "1.0")),
         enhance_hop_s=float(os.environ.get("ENHANCE_HOP_S", "0.2")),
         beamform_mode=os.environ.get("BEAMFORM_MODE", "auto").lower(),
+        torch_num_threads=int(os.environ.get("TORCH_NUM_THREADS", "1")),
         publish_timeout_s=float(os.environ.get("PUBLISH_TIMEOUT_S", "60")),
         log_level=os.environ.get("LOG_LEVEL", "INFO").upper(),
         cameras=_parse_cameras(os.environ.get("CAMERAS", "all")),
@@ -96,4 +98,6 @@ def load_config(env_path: Optional[Path] = None) -> Config:
     if cfg.beamform_mode not in ("auto", "force", "off"):
         raise ValueError(
             f"BEAMFORM_MODE must be auto|force|off, got {cfg.beamform_mode}")
+    if cfg.torch_num_threads < 1:
+        raise ValueError("TORCH_NUM_THREADS must be >= 1")
     return cfg