zhhuang-nv 97bc680cd8 feat: support kv cache reuse for MLA (#3571) ... * support kv cache reuse for MLA load compressed_kv and k_pe and do up-projection use 192/128 head size MLA context kernel support Blackwell and Hopper now Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * add CI test Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * fix: set k_pe head_num to 1 for kernel 2 and kernel 2V2 Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com> * resolve comments Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * use GPTJ style RoPE for MLA Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * fix rebase error and some docs Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * fix kv_lens Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * tiny fix Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * fix torch compile Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * fix: use normal device memory instead of pinned memory for unit test Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com> * fix L0 tests Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * fix torch compile after rebase 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> * resolve comments again Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> --------- Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com> Signed-off-by: zhhuang-nv <145532724+zhhuang-nv@users.noreply.github.com> Co-authored-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>		2025-05-15 15:22:21 +08:00
..
cubin	feat: support kv cache reuse for MLA (#3571)	2025-05-15 15:22:21 +08:00
CMakeLists.txt	infra: open source fmha v2 kernels (#4185)	2025-05-15 10:56:34 +08:00
fmhaPackedMask.cu	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
fmhaPackedMask.h	Update TensorRT-LLM (#2783)	2025-02-13 18:40:22 +08:00
fmhaRunner.cpp	feat: support kv cache reuse for MLA (#3571)	2025-05-15 15:22:21 +08:00
fmhaRunner.h	Update TensorRT-LLM (#2363)	2024-10-22 20:27:35 +08:00
fused_multihead_attention_common.h	feat: support kv cache reuse for MLA (#3571)	2025-05-15 15:22:21 +08:00
fused_multihead_attention_v2.cpp	feat: Add support for FP8 MLA on Hopper and Blackwell. (#3190)	2025-04-07 15:14:13 +08:00
fused_multihead_attention_v2.h	feat: Add support for FP8 MLA on Hopper and Blackwell. (#3190)	2025-04-07 15:14:13 +08:00
tmaDescriptor.h	Update TensorRT-LLM (#1274)	2024-03-12 18:15:52 +08:00