Promote prefix_cache_retention_interval to an argument and change the default to 0 (#52216)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com> Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
co-authored by
OpenAI Codex
parent
1d3a8b9e22
commit
017e9f4448
@@ -1433,7 +1433,7 @@ class MooncakeStoreWorker:
|
||||
scheduler_block_size=self.block_size,
|
||||
hash_block_size=self.hash_block_size,
|
||||
use_eagle=use_eagle,
|
||||
retention_interval=envs.VLLM_PREFIX_CACHE_RETENTION_INTERVAL,
|
||||
retention_interval=kv_cache_config.prefix_cache_retention_interval,
|
||||
)
|
||||
# One ChunkedTokenDatabase per group; addresses populated in
|
||||
# register_kv_caches once the kv-cache layout is known. Each group's
|
||||
|
||||
Reference in New Issue
Block a user