ColossalAI/colossalai/kernel/cuda_native
flybird1111 7a3dfd0c64 [shardformer] update shardformer to use flash attention 2 (#4392)
* cherry-pick flash attention 2

cherry-pick flash attention 2

* [shardformer] update shardformer to use flash attention 2

[shardformer] update shardformer to use flash attention 2, fix

[shardformer] update shardformer to use flash attention 2, fix

[shardformer] update shardformer to use flash attention 2, fix
2023-08-15 23:25:14 +08:00
..
csrc [bf16] add bf16 support (#3882) 2023-06-05 15:58:31 +08:00
mha [coloattention] fix import error (#4380) 2023-08-04 16:28:41 +08:00
__init__.py [shardformer] update shardformer to use flash attention 2 (#4392) 2023-08-15 23:25:14 +08:00
layer_norm.py [kernel] fixed repeated loading of kernels (#2549) 2023-02-03 09:47:13 +08:00
multihead_attention.py [nfc] fix typo colossalai/cli fx kernel (#3847) 2023-06-02 15:02:45 +08:00
scaled_softmax.py [fix] coloattention support flash attention 2 (#4347) 2023-08-04 13:46:22 +08:00