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
..
batch_manager	feat: support kv cache reuse for MLA (#3571)	2025-05-15 15:22:21 +08:00
common	feat: support kv cache reuse for MLA (#3571)	2025-05-15 15:22:21 +08:00
cutlass_extensions/include/cutlass_extensions	[TRTLLM-3330][feat] Support DeepSeek-R1 W4A8 on Hopper (#4123)	2025-05-14 15:48:07 +08:00
executor	[TRTLLM-5171] chore: Remove GptSession/V1 from TRT workflow (#4092)	2025-05-14 23:10:04 +02:00
executor_worker	Update TensorRT-LLM (#2792)	2025-02-18 21:27:39 +08:00
kernels	feat: support kv cache reuse for MLA (#3571)	2025-05-15 15:22:21 +08:00
layers	Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979)	2025-05-12 22:32:29 +02:00
plugins	fix: Eagle decoding in TRT flow (#4229)	2025-05-14 16:10:49 +02:00
pybind	Revert "feat: Low Precision Allreduce for PCIe based GPU" (#4340)	2025-05-15 09:52:39 +08:00
runtime	[TRTLLM-5171] chore: Remove GptSession/V1 from TRT workflow (#4092)	2025-05-14 23:10:04 +02:00
testing	refactor: Move ModelSpec to core library (#3980)	2025-05-04 01:39:09 +08:00
thop	feat: support kv cache reuse for MLA (#3571)	2025-05-15 15:22:21 +08:00
CMakeLists.txt	Cherry-pick trtllm-gen from feat/llama4 to main (#4086)	2025-05-08 14:13:01 -07:00