TensorRT-LLMs/tensorrt_llm/_torch/distributed
Chuang Zhu 77657a1c12
[TRTLLM-7361][feat] KV cache transfer for uneven pp (#7117)
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
2025-09-08 13:37:46 -04:00
..
__init__.py [TRTLLM-3927] [feat] Finalize + Allreduce + add + rmsnorm fusion (#4756) 2025-06-10 19:55:16 +08:00
communicator.py [TRTLLM-7361][feat] KV cache transfer for uneven pp (#7117) 2025-09-08 13:37:46 -04:00
ops.py [https://nvbugs/5445466][fix] Bypass MLP TP split for MNNVL in DeepSeek V3 to avoid hanging. (#6886) 2025-08-28 15:17:48 -07:00