mirror of https://github.com/hpcaitech/ColossalAI
e2c0e7f92a
* [hotfix] remove triton kernels from kernel init * revise bloom/llama kernel imports for infer |
||
---|---|---|
.. | ||
__init__.py | ||
context_attention.py | ||
copy_kv_cache_dest.py | ||
fused_layernorm.py | ||
qkv_matmul_kernel.py | ||
rms_norm.py | ||
rotary_embedding_kernel.py | ||
self_attention_nofusion.py | ||
softmax.py | ||
token_attention_kernel.py |