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
..
algorithms.cpp	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
algorithms.h	Update TensorRT-LLM (#2413)	2024-11-05 16:27:06 +08:00
bindings.cpp	Update (#2978)	2025-03-23 16:39:35 +08:00
bindings.h	Update TensorRT-LLM (#2413)	2024-11-05 16:27:06 +08:00
buffers.cpp	Update TensorRT-LLM (#2849)	2025-03-04 18:44:00 +08:00
buffers.h	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
cacheTransceiver.cpp	Update TensorRT-LLM (#2849)	2025-03-04 18:44:00 +08:00
cacheTransceiver.h	Update TensorRT-LLM (#2820)	2025-02-25 21:21:49 +08:00
kvCacheManager.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
kvCacheManager.h	Update TensorRT-LLM (#2413)	2024-11-05 16:27:06 +08:00
llmRequest.cpp	Update TensorRT-LLM (#2582)	2024-12-16 21:50:47 -08:00
llmRequest.h	Update TensorRT-LLM (#2582)	2024-12-16 21:50:47 -08:00