A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 04:45 UTC
[BugFix] Fix the incorrect func name in the comments. (config.py) (#20185)
Jiayi Yan committed
Jun 28, 2025 at 13:51 UTC
7b460c25f987dfb6ca7cebc7d1e2c26989801674
1 file changed
+1
-1
vllm/config.py
+1
-1
@@ -1484,7 +1484,7 @@ class CacheConfig:
1484
sizes up to 32 are supported. On HPU devices, block size defaults to 128.
1485
1486
This config has no static default. If left unspecified by the user, it will
1487
- be set in `Platform.check_and_update_configs()` based on the current
1487
+ be set in `Platform.check_and_update_config()` based on the current
1488
platform."""
1489
gpu_memory_utilization: float = 0.9
1490
"""The fraction of GPU memory to be used for the model executor, which can