server : fix tests to pass --no-slots when necessary

Author: ggerganov

tools/server/README.md

@@ -185,8 +185,8 @@ The project is under active development, and we are [looking for feedback and co
 | `--threads-http N` | number of threads used to process HTTP requests (default: -1)<br/>(env: LLAMA_ARG_THREADS_HTTP) |
 | `--cache-reuse N` | min chunk size to attempt reusing from the cache via KV shifting (default: 0)<br/>[(card)](https://ggml.ai/f0.png)<br/>(env: LLAMA_ARG_CACHE_REUSE) |
 | `--metrics` | enable prometheus compatible metrics endpoint (default: disabled)<br/>(env: LLAMA_ARG_ENDPOINT_METRICS) |
-| `--slots` | enable slots monitoring endpoint (default: disabled)<br/>(env: LLAMA_ARG_ENDPOINT_SLOTS) |
 | `--props` | enable changing global properties via POST /props (default: disabled)<br/>(env: LLAMA_ARG_ENDPOINT_PROPS) |
+| `--slots` | enable slots monitoring endpoint (default: enabled)<br/>(env: LLAMA_ARG_ENDPOINT_SLOTS) |
 | `--no-slots` | disables slots monitoring endpoint<br/>(env: LLAMA_ARG_NO_ENDPOINT_SLOTS) |
 | `--slot-save-path PATH` | path to save slot kv cache (default: disabled) |
 | `--jinja` | use jinja template for chat (default: disabled)<br/>(env: LLAMA_ARG_JINJA) |

tools/server/tests/utils.py

@@ -148,6 +148,8 @@ def start(self, timeout_seconds: int | None = DEFAULT_HTTP_TIMEOUT) -> None:
             server_args.append("--metrics")
         if self.server_slots:
             server_args.append("--slots")
+        else:
+            server_args.append("--no-slots")
         if self.pooling:
             server_args.extend(["--pooling", self.pooling])
         if self.model_alias: