Junhong Liu 06e76020d7 feat: parallel q_b_proj and concat (#3917) ... * add parallel_q_b_proj_and_concat Signed-off-by: junliu <65336694+hello-11@users.noreply.github.com> * code cleanup Signed-off-by: junliu <65336694+hello-11@users.noreply.github.com> * one gemm/concat and then split the latent_cache and pass them separately to context/gen Signed-off-by: junliu <65336694+hello-11@users.noreply.github.com> --------- Signed-off-by: junliu <65336694+hello-11@users.noreply.github.com>		2025-04-29 22:07:05 +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: parallel q_b_proj and concat (#3917)	2025-04-29 22:07:05 +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	Fix fp8 kvcache (#3877)	2025-04-29 10:31:10 +08:00
gated_mlp.py	Fix create_weights in attention (#3692)	2025-04-24 07:30:00 +08:00
linear.py	Fix fp8 kvcache (#3877)	2025-04-29 10:31:10 +08:00
logits_procesor.py	Update (#2978)	2025-03-23 16:39:35 +08:00
mlp.py	Fix create_weights in attention (#3692)	2025-04-24 07:30:00 +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	fix: llama4: address couple of issues in llama4 attention module (#3491)	2025-04-18 01:54:59 +00:00
rotary_embedding.py	feat: Support cos_sin_cache in all cases. (#3517)	2025-04-16 13:48:44 +08:00