github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-06 19:40:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

[Inference/NFC] Clean outdated inference tests and deprecated kernels (#5159)

Browse Source 
* [inference/nfc] remove outdated inference tests

* remove outdated kernel tests

* remove deprecated triton kernels

* remove imports from deprecated kernels
This commit is contained in:
Yuanheng Zhao
2023-12-05 15:12:57 +08:00
committed by FrankLeeeee
parent 56e75eeb06
commit 2bb92243d4
18 changed files with 0 additions and 2543 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
colossalai/kernel/triton/__init__.py
View File

@@ -8,24 +8,12 @@ except ImportError:
# There may exist import error even if we have triton installed.
if HAS_TRITON:
from .context_attention import bloom_context_attn_fwd, llama_context_attn_fwd
from .copy_kv_cache_dest import copy_kv_cache_to_dest
from .fused_layernorm import layer_norm
from .gptq_triton import gptq_fused_linear_triton
from .int8_rotary_embedding_kernel import int8_rotary_embedding_fwd
from .smooth_attention import smooth_llama_context_attn_fwd, smooth_token_attention_fwd
from .softmax import softmax
from .token_attention_kernel import token_attention_fwd
__all__ = [
"llama_context_attn_fwd",
"bloom_context_attn_fwd",
"softmax",
"layer_norm",
"copy_kv_cache_to_dest",
"token_attention_fwd",
"gptq_fused_linear_triton",
"int8_rotary_embedding_fwd",
"smooth_llama_context_attn_fwd",
"smooth_token_attention_fwd",
]