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
..
test_allreduce.py	Unify two versions of AllReduce custom op (#3032)	2025-04-22 21:58:42 +08:00
test_ar_residual_norm.py	refactor: remove ParallelConfig in tensorrt_llm._torch.distributed module (#3370)	2025-04-11 15:34:20 -07:00
test_deepseek_allreduce.py	Unify two versions of AllReduce custom op (#3032)	2025-04-22 21:58:42 +08:00
test_embedding.py	refactor: remove ParallelConfig in tensorrt_llm._torch.distributed module (#3370)	2025-04-11 15:34:20 -07:00
test_linear.py	refactor: remove ParallelConfig in tensorrt_llm._torch.distributed module (#3370)	2025-04-11 15:34:20 -07:00
test_star_attention_input.jsonl	Update TensorRT-LLM (#2936)	2025-03-18 21:25:19 +08:00
test_star_attention.py	feat: Support cos_sin_cache in all cases. (#3517)	2025-04-16 13:48:44 +08:00
test_user_buffers.py	fix: Remove ParallelConfig. (#3678)	2025-04-21 14:14:08 +08:00