Sage 1651003c35 [Prefix Cache] Use LoRA name for consistent KV-cache block hashing (#27211) ...

Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>

2025-10-22 18:13:03 +00:00

..

sched

[Minor] Add some clarifying comments to recent changes (#27130)

2025-10-18 09:52:45 -07:00

__init__.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

block_pool.py

[Core] Reuse empty block lists whenever possible in KVCacheBlocks to mitigate GC costs (#24964)

2025-10-14 12:58:43 -07:00

encoder_cache_manager.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

kv_cache_coordinator.py

[Core] Reuse empty block lists whenever possible in KVCacheBlocks to mitigate GC costs (#24964)

2025-10-14 12:58:43 -07:00

kv_cache_manager.py

[Easy] Get rid of unnecessary paraenthesis in kv_cache_manager (#26842)

2025-10-15 09:17:43 +00:00

kv_cache_utils.py

[Prefix Cache] Use LoRA name for consistent KV-cache block hashing (#27211)

2025-10-22 18:13:03 +00:00

single_type_kv_cache_manager.py

[Core] Reuse empty block lists whenever possible in KVCacheBlocks to mitigate GC costs (#24964)

2025-10-14 12:58:43 -07:00