biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bugfix] fix confusing OOM errors during v1 init (#28051)

Browse Source 
Signed-off-by: Shivam <shivamprasad91@gmail.com>
Signed-off-by: shivampr <shivampr.dev@gmail.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
This commit is contained in:
shivampr
2025-12-10 15:17:41 -08:00
committed by GitHub
parent 166ac3c94d
commit 8580919ac3
3 changed files with 138 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/v1/core/kv_cache_utils.py
View File

@@ -687,7 +687,9 @@ def check_enough_kv_cache_memory(
raise ValueError(
"No available memory for the cache blocks. "
"Try increasing `gpu_memory_utilization` when "
"initializing the engine."
"initializing the engine. "
"See https://docs.vllm.ai/en/latest/configuration/conserving_memory/ "
"for more details."
)
max_model_len = vllm_config.model_config.max_model_len
@@ -711,8 +713,10 @@ def check_enough_kv_cache_memory(
f"cache is needed, which is larger than the available KV cache "
f"memory ({available_memory / GiB_bytes:.2f} GiB). "
f"{estimated_msg} "
f"Try increasing `gpu_memory_utilization` or decreasing "
f"`max_model_len` when initializing the engine."
f"Try increasing `gpu_memory_utilization` 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."
)