xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-14 07:25:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Fix estimated max model len msg (#18966)

Browse Source 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
This commit is contained in:
Yong Hoon Shin 2025-05-31 01:43:44 -07:00 committed by GitHub
parent dff80b0e42
commit 1e123529d7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/v1/core/kv_cache_utils.py
View File

@ -544,8 +544,9 @@ def check_enough_kv_cache_memory(vllm_config: VllmConfig,
available_memory) available_memory)
estimated_msg = "" estimated_msg = ""
if estimated_max_len > 0: if estimated_max_len > 0:
estimated_msg = " Based on the available memory," estimated_msg = (
f" the estimated maximum model length is {estimated_max_len}." "Based on the available memory, "
f"the estimated maximum model length is {estimated_max_len}.")
raise ValueError( 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 models's max seq len "