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 14, 05:30 UTC
[Misc] add hash_function doc string (#24014)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Ning Xie committed
Sep 1, 2025 at 14:11 UTC
5438967fbc7a10ae6eee7a98182f4de94101e858
1 file changed
+1
vllm/v1/core/kv_cache_utils.py
+1
@@ -527,6 +527,7 @@ def hash_block_tokens(
527
hash values for the same block contents.
528
529
Args:
530
+ hash_function: The hash function used to compute block hash.
531
parent_block_hash: The hash of the parent block. None
532
if this is the first block.
533
curr_block_token_ids: A list of token ids in the current