Dean LeitersdorfandGitHub 79af7e96a0 [OPTIMIZATION] Optimizes the single_query_cached_kv_attention kernel (#420)

2023-08-04 10:57:29 -07:00

..

attention

[OPTIMIZATION] Optimizes the single_query_cached_kv_attention kernel (#420)

2023-08-04 10:57:29 -07:00

activation_kernels.cu

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00

activation.cpp

Optimize data movement (#20)

2023-04-02 00:30:17 -07:00

attention.cpp

Optimize MQA Kernel (#452)

2023-07-14 20:06:40 -04:00

cache_kernels.cu

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00

cache.cpp

Memcpy kernel for flash attention (#29)

2023-04-10 18:22:49 -07:00

layernorm_kernels.cu

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00

layernorm.cpp

Add custom kernel for RMS normalization (#16)

2023-04-01 00:51:22 +08:00

pos_encoding_kernels.cu

Add Falcon support (new) (#592)

2023-08-02 14:04:39 -07:00

pos_encoding.cpp

Add support for GPT-NeoX (Pythia) (#50)

2023-04-28 00:32:10 -07:00

reduction_utils.cuh

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00