Yukun He fd4311e6a3 [TRTLLM-8129][feat] Allreduce tuning and benchmark script revising (#7870) ... Because we have encountered some perf regression due to using a one-shot kernel instead of NCCL on A100/H100, it will be beneficial if we can have a solid benchmarking of allreduce Op and analyze the data collected from it. Implemented new AllreduceOp heuristic: - Added Linear programming-based heuristic implementation. - Added LUT-based heuristic implementation and corresponding code generation script. AllreduceOp minor fixing: - Fixed a minor issue in AllreduceOp, that the strategy can not be overridden when ONESHOT or TWOSHOT is set. - Fixed a minor TWOSHOT kernel perf issue. - Cleaned up Dispatching code in AllReduceOp. This PR will fix the perf gaps reported in: https://nvbugspro.nvidia.com/bug/5517023 For Deepseek-R1, it shows a performance gain of about 3-4% in concurrency levels of 256 and 512. Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>		2025-10-16 14:15:25 +08:00
..
allreduce_perf	[TRTLLM-8129][feat] Allreduce tuning and benchmark script revising (#7870)	2025-10-16 14:15:25 +08:00
perf-sanity	[TRTLLM-7157][feat] BREAKING CHANGE Introduce sampler_type, detect sampler according to options (#6831)	2025-08-16 00:27:24 -04:00