xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 15:44:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

[MISC] add cpu_kvcache_space_bytes to CacheConfig (#19812)

Browse Source 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
This commit is contained in:
Ning Xie 2025-06-22 13:39:09 +08:00 committed by GitHub
parent 4c409cabc2
commit 2bb246b8f7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/config.py
View File

@ -1506,6 +1506,8 @@ class CacheConfig:
"""This enables dynamic calculation of `k_scale` and `v_scale` when
kv_cache_dtype is fp8. If `False`, the scales will be loaded from the model
checkpoint if available. Otherwise, the scales will default to 1.0."""
cpu_kvcache_space_bytes: Optional[int] = None
"""(CPU backend only) CPU key-value cache space."""
# Will be set after profiling.
num_gpu_blocks: Optional[int] = field(default=None, init=False)