ColossalAI/colossalai/inference/modeling/layers
Yuanheng Zhao fa85e02b3b
[kernel] Add KV cache copy kernel during decoding (#5261)
* add kv copy triton kernel during decoding stage

* add pytest and fix kernel

* fix test utilities

* revise kernel config

* add benchmark for kvcache copy
2024-01-15 17:37:20 +08:00
..
attention.py [kernel] Add KV cache copy kernel during decoding (#5261) 2024-01-15 17:37:20 +08:00