misc

packages/node/meshnet_node/torch_server.py

@@ -368,7 +368,11 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
         if stream:
             stream_emit = self._start_openai_stream(model_name)
 
-        for _ in range(max_tokens):
+        _GENERATION_LOG_INTERVAL = 5.0
+        gen_started = time.monotonic()
+        last_gen_log = gen_started
+
+        for step in range(max_tokens):
             try:
                 payload = backend.encode_prompt(current_text)
             except Exception as exc:
@@ -386,6 +390,21 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
             if stream_emit is not None:
                 stream_emit(token_str)
             current_text = current_text + token_str
+            now = time.monotonic()
+            if step == 0 or now - last_gen_log >= _GENERATION_LOG_INTERVAL:
+                print(
+                    f"  [node] generating step={step + 1}/{max_tokens} "
+                    f"tokens={len(generated)} elapsed_s={now - gen_started:.1f}",
+                    flush=True,
+                )
+                last_gen_log = now
+
+        if generated:
+            print(
+                f"  [node] generation complete tokens={len(generated)} "
+                f"elapsed_s={time.monotonic() - gen_started:.1f}",
+                flush=True,
+            )
 
         result_text = "".join(generated)
         if stream_emit is not None: