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
..
batch_manager	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
common	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
deep_gemm	Update TensorRT-LLM (#2936)	2025-03-18 21:25:19 +08:00
executor	Update (#2978)	2025-03-23 16:39:35 +08:00
kernels	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
layers	Update TensorRT-LLM (#2820)	2025-02-25 21:21:49 +08:00
plugins/api	Update TensorRT-LLM (#2532)	2024-12-04 21:16:56 +08:00
runtime	Update (#2978)	2025-03-23 16:39:35 +08:00