Yukun He 0ae7017342 Unify two versions of AllReduce custom op (#3032) ... * Rewrite unit test for unified allreduce op. Removing the legacy unit test. * Revise formats, fusion_op bindings. Put all tensors as optional inputs. * Move the MoeAllreduceOp to a separate custom op. * Move all the fusion patterns to the new version of the AllReduce fusion kernel. Remove the AllReduce strategy config. Revise the AllReduce strategies and fusion pattern definitions. * Add more TODOs, fixing minor bugs, and remove legacy code. Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>		2025-04-22 21:58:42 +08:00
..
batch_manager	refactor: Introduce DecoderOutputBuffers per batch (#3506)	2025-04-22 12:25:53 +08:00
common	feat: support abort disconnected requests (#3214)	2025-04-07 16:14:58 +08:00
executor	feat: Offloading Multimodal embedding table to CPU in Chunked Prefill Mode (#3380)	2025-04-21 14:31:01 +08:00
runtime	Unify two versions of AllReduce custom op (#3032)	2025-04-22 21:58:42 +08:00
userbuffers	feat: Introduce UB allocator for pytorch flow (#3257)	2025-04-08 18:39:49 +08:00
bindings.cpp	feat: Integrate GPUDirect Storage (GDS) into Executor API (#3582)	2025-04-18 15:59:21 +08:00
CMakeLists.txt	Update TensorRT-LLM (#2849)	2025-03-04 18:44:00 +08:00