Fridah-nv d008d6412f feat:[AutoDeploy] Update MoE pattern matcher to drop expert selection logic (#3283) ... * update matcher to match expert compute first, then extract other args with LCA Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com> * support 3D and 2D input in torch.ops.moe.trtllm_fused_moe Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com> * update custom ops to support 3D and 2D inputs Signed-off-by: Ubuntu <201670829+Fridah-nv@users.noreply.github.com> * update deepseek patch Signed-off-by: Ubuntu <201670829+Fridah-nv@users.noreply.github.com> --------- Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>		2025-05-15 13:53:09 +08:00
..
compile	feat: [AutoDeploy] generalizing cudagraph to multiple dynamic inputs (#3589)	2025-04-23 03:38:51 +08:00
custom_ops	feat:[AutoDeploy] Update MoE pattern matcher to drop expert selection logic (#3283)	2025-05-15 13:53:09 +08:00
distributed	[AutoDeploy] Make all ranks agree on kv-cache size (#4007)	2025-05-02 04:07:28 +08:00
models	feat:[AutoDeploy] Update MoE pattern matcher to drop expert selection logic (#3283)	2025-05-15 13:53:09 +08:00
shim	[AutoDeploy][perf] Further optimize flashinfer backend in AutoDeploy (#4024)	2025-05-06 10:46:36 +08:00
transformations	feat:[AutoDeploy] Update MoE pattern matcher to drop expert selection logic (#3283)	2025-05-15 13:53:09 +08:00
utils	feat: [AutoDeploy] unfusing attention for native support (#3668)	2025-05-02 09:06:49 +08:00
__init__.py	Update TensorRT-LLM (#2820)	2025-02-25 21:21:49 +08:00