vllm.utils.cache Âķ
Classes:
-
LRUCacheâ
LRUCache Âķ
Bases: LRUCache[_K, _V]
Methods:
-
pinâPins a key in the cache preventing it from being
-
popitemâRemove and return the
(key, value)pair least recently used. -
statâGets the cumulative number of hits and queries against this cache.
Attributes:
-
cache(Mapping[_K, _V]) âReturn the internal cache dictionary in order (read-only).
-
order(Mapping[_K, None]) âReturn the internal order dictionary (read-only).
Source code in vllm/utils/cache.py
51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 | |
cache property Âķ
Return the internal cache dictionary in order (read-only).
order property Âķ
Return the internal order dictionary (read-only).
_unpin(key) Âķ
pin(key) Âķ
Pins a key in the cache preventing it from being evicted in the LRU order.
popitem(remove_pinned=False) Âķ
Remove and return the (key, value) pair least recently used.
Source code in vllm/utils/cache.py
stat(*, delta=False) Âķ
Gets the cumulative number of hits and queries against this cache.
If delta=True, instead gets these statistics since the last call that also passed delta=True.