Woosuk Kwon 8ce9c50d40 Avoid compiling kernels for double data type (#933)		2023-09-02 14:59:47 +09:00
..
attention	[OPTIMIZATION] Optimizes the single_query_cached_kv_attention kernel (#420)	2023-08-04 10:57:29 -07:00
activation.cpp	Implement approximate GELU kernels (#828)	2023-08-23 07:43:21 +09:00
activation_kernels.cu	Avoid compiling kernels for double data type (#933)	2023-09-02 14:59:47 +09:00
attention.cpp	Optimize MQA Kernel (#452)	2023-07-14 20:06:40 -04:00
cache.cpp	Memcpy kernel for flash attention (#29)	2023-04-10 18:22:49 -07:00
cache_kernels.cu	Avoid compiling kernels for double data type (#933)	2023-09-02 14:59:47 +09:00
dispatch_utils.h	Avoid compiling kernels for double data type (#933)	2023-09-02 14:59:47 +09:00
layernorm.cpp	Add custom kernel for RMS normalization (#16)	2023-04-01 00:51:22 +08:00
layernorm_kernels.cu	Avoid compiling kernels for double data type (#933)	2023-09-02 14:59:47 +09:00
pos_encoding.cpp	Add support for GPT-NeoX (Pythia) (#50)	2023-04-28 00:32:10 -07:00
pos_encoding_kernels.cu	Avoid compiling kernels for double data type (#933)	2023-09-02 14:59:47 +09:00
reduction_utils.cuh	Change the name to vLLM (#150)	2023-06-17 03:07:40 -07:00