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

Add warning

Browse Source
This commit is contained in:
Woosuk Kwon 2023-02-16 01:28:17 +00:00
parent 2f4887de77
commit 8edcabc737
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
cacheflow/worker/cache_engine.py
View File

@ -19,6 +19,9 @@ class CacheEngine:
num_cpu_blocks: int, num_cpu_blocks: int,
dtype: torch.dtype, dtype: torch.dtype,
) -> None: ) -> None:
if head_size % 16 != 0:
raise ValueError(f'head_size ({head_size}) must be a multiple of 16.')
self.worker_id = worker_id self.worker_id = worker_id
self.gpu_id = gpu_id self.gpu_id = gpu_id
self.num_layers = num_layers self.num_layers = num_layers