From ab5666eb7cb5a98f2ff260523c9aa469da23a004 Mon Sep 17 00:00:00 2001 From: Matthew Bonanni Date: Tue, 21 Apr 2026 11:26:06 -0400 Subject: [PATCH] [UX] Bump version in CG memory profiling log message (#40465) Signed-off-by: Matthew Bonanni --- vllm/v1/worker/gpu_worker.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/vllm/v1/worker/gpu_worker.py b/vllm/v1/worker/gpu_worker.py index 4a73eddcdb..ec8f9c6dd3 100644 --- a/vllm/v1/worker/gpu_worker.py +++ b/vllm/v1/worker/gpu_worker.py @@ -456,7 +456,7 @@ class Worker(WorkerBase): logger.info( "CUDA graph memory profiling is enabled " "(VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=1). " - "This will become the default in v0.19. " + "This will become the default in v0.21. " "The current --gpu-memory-utilization=%.4f is equivalent " "to --gpu-memory-utilization=%.4f without CUDA graph " "memory profiling. To maintain the same effective KV " @@ -472,7 +472,7 @@ class Worker(WorkerBase): 1.0, ) logger.info( - "In v0.19, CUDA graph memory profiling will be enabled " + "In v0.21, CUDA graph memory profiling will be enabled " "by default (VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=1), " "which more accurately accounts for CUDA graph memory " "during KV cache allocation. To try it now, set "