TensorRT-LLMs/tensorrt_llm/_torch/distributed
Bo Li e405468230
[TRTLLM-10048][feat] Fuse the AllGather for expert statistics required by the EPLB. (#10885)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
2026-01-26 17:59:03 +08:00
..
__init__.py
communicator.py
moe_alltoall.py [TRTLLM-10048][feat] Fuse the AllGather for expert statistics required by the EPLB. (#10885) 2026-01-26 17:59:03 +08:00
ops.py [https://nvbugs/5782112][fix] Cherry-pick #10633: Fix hanging issue for MNNVL Allreduce under PP (#10750) 2026-01-25 18:12:21 +08:00
pg_utils.py
symm_mem_allreduce.py