Warmup cublas (#566)

2024-06-25 12:46:00 -07:00
parent eb1ae6ae0c
commit a385ee27bd
6 changed files with 17 additions and 4 deletions
--- a/python/sglang/srt/managers/controller/tp_worker.py
+++ b/python/sglang/srt/managers/controller/tp_worker.py
@@ -410,7 +410,7 @@ class ModelTpServer:
                self.tree_cache_metrics["hit"] / self.tree_cache_metrics["total"]
            )
            logger.info(
-                f"[gpu_id={self.gpu_id}] Prefil batch. "
+                f"[gpu_id={self.gpu_id}] Prefill batch. "
                f"#new-seq: {len(can_run_list)}, "
                f"#new-token: {new_batch_input_tokens}, "
                f"#cached-token: {hit_tokens}, "