ModelLink2/modellink/core/tensor_parallel
2024-08-31 01:13:32 +00:00
..
ascend_turbo !1447 增加mixtral_mcore,增加mcore的mc2以及优化dispatcher亲和化操作argsort 2024-07-22 14:01:20 +00:00
__init__.py !1246 更新baichuan2-13B性能至1668 2024-04-26 01:47:52 +00:00
layers.py !1578 [mcore-llm]类deepseekv2模型性能优化:无tp场景下的大词表mm本地切分,并支持mla场景的指定softmax_scale 2024-08-31 01:13:32 +00:00