Netanel Haber da0b0e0ee3 fix: disable kv cache reuse when minimum window size is reached, instead of maximum window size (#2983) ... * fix variable window size reuse - disable when *min attention window* starts sliding, not max * isPreCyclic -> isCyclic, and invert logic, for clarity * getDecoderState() Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>		2025-03-24 22:49:52 +08:00
..
capacitySchedulerTest.cpp	fix: disable kv cache reuse when minimum window size is reached, instead of maximum window size (#2983)	2025-03-24 22:49:52 +08:00
CMakeLists.txt	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
contextProgressTest.cu	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
evictionPolicyTest.cpp	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
kvCacheManagerTest.cpp	fix: disable kv cache reuse when minimum window size is reached, instead of maximum window size (#2983)	2025-03-24 22:49:52 +08:00
kvCacheUtilsTest.cpp	fix: disable kv cache reuse when minimum window size is reached, instead of maximum window size (#2983)	2025-03-24 22:49:52 +08:00
llmRequestTest.cpp	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
microBatchSchedulerTest.cpp	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
staticThreadPoolTest.cpp	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00