You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

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>		1 year ago
..
__init__.py	[Inference] Dynamic Batching Inference, online and offline (#4953)	1 year ago
context_attention.py	[Kernels]added flash-decoidng of triton (#5063)	1 year ago
copy_kv_cache_dest.py	[Inference] Dynamic Batching Inference, online and offline (#4953)	1 year ago
custom_autotune.py	add autotune (#4822)	1 year ago
flash_decoding.py	[Kernels]added flash-decoidng of triton (#5063)	1 year ago
fused_layernorm.py	[misc] update pre-commit and run all files (#4752)	1 year ago
gptq_triton.py	[inference] add reference and fix some bugs (#4937)	1 year ago
int8_rotary_embedding_kernel.py	[inference] Add smmoothquant for llama (#4904)	1 year ago
llama_act_combine_kernel.py	[moe] merge moe into main (#4978)	1 year ago
qkv_matmul_kernel.py	[misc] update pre-commit and run all files (#4752)	1 year ago
self_attention_nofusion.py	[Refactor] Integrated some lightllm kernels into token-attention (#4946)	1 year ago
smooth_attention.py	[inference] add reference and fix some bugs (#4937)	1 year ago
softmax.py	[misc] update pre-commit and run all files (#4752)	1 year ago
token_attention_kernel.py	[Kernels]Update triton kernels into 2.1.0 (#5046)	1 year ago