[Bugfix] Clarify CPU backend memory error messages reference shared flag (#42479)

Signed-off-by: daniel-devlab <282598346+daniel-devlab@users.noreply.github.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
Daniel W
2026-05-15 06:35:05 +00:00
committed by GitHub
co-authored by Li, Jiang <jiang1.li@intel.com>
parent e30f39c4f1
commit 27b85d2084
2 changed files with 11 additions and 5 deletions
+6 -3
View File
@@ -697,7 +697,9 @@ def _check_enough_kv_cache_memory(
if available_memory <= 0:
raise ValueError(
"No available memory for the cache blocks. "
"Try increasing `gpu_memory_utilization` when initializing the engine. "
"Try increasing `gpu_memory_utilization` when initializing the engine "
"(this flag also controls CPU memory reservation on the CPU "
"backend, despite its name). "
"See https://docs.vllm.ai/en/latest/configuration/conserving_memory/ "
"for more details."
)
@@ -714,11 +716,12 @@ def _check_enough_kv_cache_memory(
)
raise ValueError(
f"To serve at least one request with the models's max seq len "
f"To serve at least one request with the model's max seq len "
f"({max_model_len}), ({format_gib(needed_memory)} GiB KV "
f"cache is needed, which is larger than the available KV cache "
f"memory ({format_gib(available_memory)} GiB). {estimated_msg}"
f"Try increasing `gpu_memory_utilization` or decreasing `max_model_len` "
f"Try increasing `gpu_memory_utilization` (which also controls "
f"CPU memory on the CPU backend) or decreasing `max_model_len` "
f"when initializing the engine. "
f"See https://docs.vllm.ai/en/latest/configuration/conserving_memory/ "
f"for more details."
+5 -2
View File
@@ -71,8 +71,11 @@ class CPUWorker(Worker):
f"is less than desired CPU memory utilization "
f"({vllm_config.cache_config.gpu_memory_utilization}, "
f"{format_gib(self.requested_cpu_memory)} GiB). "
"Decrease --gpu-memory-utilization"
f" or reduce CPU memory used by other processes."
"On the CPU backend, the `--gpu-memory-utilization` flag "
"controls the fraction of CPU memory reserved (despite its "
"name). To resolve: decrease `--gpu-memory-utilization` "
"(e.g. `--gpu-memory-utilization 0.5`) "
"or reduce CPU memory used by other processes."
)
super().__init__(