Cuiqing Li (李崔卿) bce919708f [Kernels]added flash-decoidng of triton (#5063) ... * added flash-decoidng of triton based on lightllm kernel * add req * clean * clean * delete build.sh --------- Co-authored-by: cuiqing.li <lixx336@gmail.com>		2023-11-20 13:58:29 +08:00
..
__init__.py	[Inference] Dynamic Batching Inference, online and offline (#4953)	2023-10-30 10:52:19 +08:00
context_attention.py	[Kernels]added flash-decoidng of triton (#5063)	2023-11-20 13:58:29 +08:00
copy_kv_cache_dest.py	[Inference] Dynamic Batching Inference, online and offline (#4953)	2023-10-30 10:52:19 +08:00
custom_autotune.py	…
flash_decoding.py	[Kernels]added flash-decoidng of triton (#5063)	2023-11-20 13:58:29 +08:00
fused_layernorm.py	…
gptq_triton.py	…
int8_rotary_embedding_kernel.py	…
llama_act_combine_kernel.py	[moe] merge moe into main (#4978)	2023-11-02 02:21:24 +00:00
qkv_matmul_kernel.py	…
self_attention_nofusion.py	…
smooth_attention.py	…
softmax.py	…
token_attention_kernel.py	[Kernels]Update triton kernels into 2.1.0 (#5046)	2023-11-16 16:43:15 +08:00