EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[minor] simplify the TokenToKVPoolAllocator (#7414)

Browse Source
This commit is contained in:
Liangsheng Yin
2025-06-22 12:37:18 +08:00
committed by GitHub
parent b7a2df0a44
commit 05c9bc8956
14 changed files with 165 additions and 149 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
python/sglang/srt/managers/cache_controller.py
View File

@@ -18,12 +18,13 @@ import logging
import math
import threading
from queue import Empty, Full, PriorityQueue, Queue
from typing import List, Optional
from typing import TYPE_CHECKING, List, Optional
import torch
from sglang.srt.mem_cache.memory_pool import TokenToKVPoolAllocator
from sglang.srt.mem_cache.memory_pool_host import HostKVCache
if TYPE_CHECKING:
from sglang.srt.mem_cache.allocator import BaseTokenToKVPoolAllocator
from sglang.srt.mem_cache.memory_pool_host import HostKVCache
logger = logging.getLogger(__name__)
@@ -163,7 +164,7 @@ class HiCacheController:
def __init__(
self,
token_to_kv_pool_allocator: TokenToKVPoolAllocator,
token_to_kv_pool_allocator: BaseTokenToKVPoolAllocator,
mem_pool_host: HostKVCache,
page_size: int,
load_cache_event: threading.Event = None,