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
..
cacheTransceiverTest.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
guidedDecoderTest.cpp	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
modelSpec.cpp	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
modelSpec.h	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
modelSpecBinding.cpp	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
peftCacheManagerTest.cpp	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
trtEncoderModelTest.cpp	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
trtGptModelRealDecoderTest.cpp	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
trtGptModelTest.cpp	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00