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
..
mamba	Fix create_weights in attention (#3692)	2025-04-24 07:30:00 +08:00
__init__.py	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
attention.py	feat: support kv cache reuse for MLA (#3571)	2025-05-15 15:22:21 +08:00
decoder_layer.py	chore: Use ellipsis as default value to detect whether residual argument is provided (#3626)	2025-04-17 12:31:58 +08:00
embedding.py	feat: llama4 input processor (#3383)	2025-04-25 16:47:14 -07:00
fused_moe.py	[TRTLLM-3330][feat] Support DeepSeek-R1 W4A8 on Hopper (#4123)	2025-05-14 15:48:07 +08:00
gated_mlp.py	feat: support multi lora adapters and TP (#3885)	2025-05-08 23:45:45 +08:00
linear.py	feat: support multi lora adapters and TP (#3885)	2025-05-08 23:45:45 +08:00
logits_processor.py	feat: LogitsProcessor in PyTorch backend (#3145)	2025-05-01 14:15:30 -07:00
mlp.py	feat: support multi lora adapters and TP (#3885)	2025-05-08 23:45:45 +08:00
multi_stream_utils.py	[chore] Make llama4 MoE use maybe_execute_in_parallel (#3779)	2025-04-28 10:58:03 -04:00
rms_norm.py	feat: Add heuristic for GroupRMSNorm kernel selection. (#4047)	2025-05-13 08:52:53 +08:00
rotary_embedding.py	feat: Add group_rms_norm kernel to normalize multiple inputs in a single operator. (#3438)	2025-05-02 13:25:30 +08:00