[CI] test chunked prefill more (#5798)

python/sglang/srt/model_executor/model_runner.py

@@ -975,7 +975,7 @@ class ModelRunner:
         after_mem = get_available_gpu_memory(self.device, self.gpu_id)
         logger.info(
             f"Capture cuda graph end. Time elapsed: {time.time() - tic:.2f} s. "
-            f"avail mem={after_mem:.2f} GB. mem usage={(before_mem - after_mem):.2f} GB."
+            f"mem usage={(before_mem - after_mem):.2f} GB. avail mem={after_mem:.2f} GB."
         )
 
     def apply_torch_tp(self):

python/sglang/srt/server_args.py

@@ -426,7 +426,7 @@ class ServerArgs:
         parser.add_argument(
             "--skip-tokenizer-init",
             action="store_true",
-            help="If set, skip init tokenizer and pass input_ids in generate request",
+            help="If set, skip init tokenizer and pass input_ids in generate request.",
         )
         parser.add_argument(
             "--enable-tokenizer-batch-encode",
@@ -565,6 +565,7 @@ class ServerArgs:
             "name, a tag name, or a commit id. If unspecified, will use "
             "the default version.",
         )
+
         # Memory and scheduling
         parser.add_argument(
             "--mem-fraction-static",