zhhuang-nv 8452775db8 [TRTLLM-5070][feat] Support FP8 KV Cache Reuse for MLA (#4535) ... * optimize kv cache reuse workflow for MLA write kv cache first and only call up-projection GEMM once relax contiguous requirements of k/v for setting paged kv cache return two contiguous tensors when loading MLA KV Cache Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * support fp8 kv cache for MLA kv cache reuse Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * resolve comments Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> --------- Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>		2025-05-23 19:47:50 +08:00
..
allReduce	fix potential issues in allreduce fusion kernel and ut (#4226)	2025-05-19 17:38:29 +08:00
cudaCoreGemm
fused_gated_gemm
sampling
smoothQuant
weightOnly
banRepeatNGramsKernelsTest.cpp
CMakeLists.txt
decodingKernelTest.cpp
logitsBitmaskTest.cpp
mixtureOfExpertsTest.cu	[https://nvbugs/5297775] fix: Correct memory guard for large MOE tests to account for TP space (#4553)	2025-05-23 14:57:49 +12:00
mlaPreprocessTest.cu	[TRTLLM-5070][feat] Support FP8 KV Cache Reuse for MLA (#4535)	2025-05-23 19:47:50 +08:00
ropeTest.cu
shiftKCacheKernelTest.cu
stopCriteriaKernelsTest.cpp