傅剑寒 808ee6e4ad [Inference/Feat] Feat quant kvcache step2 (#5674)		2024-04-30 11:26:36 +08:00
..
attention	[Inference/Kernel] Optimize paged attention: Refactor key cache layout (#5643)	2024-04-25 14:24:02 +08:00
utils	[Inference/Feat] Feat quant kvcache step2 (#5674)	2024-04-30 11:26:36 +08:00
activation_kernel.cu	…
context_kv_cache_memcpy_kernel.cu	[Inference/Feat] Feat quant kvcache step2 (#5674)	2024-04-30 11:26:36 +08:00
decode_kv_cache_memcpy_kernel.cu	…
flash_decoding_attention_kernel.cu	[Inference/Feat] Feat quant kvcache step2 (#5674)	2024-04-30 11:26:36 +08:00
fused_rotary_emb_and_cache_kernel.cu	…
get_cos_and_sin_kernel.cu	…
layer_norm_kernel.cu	…
moe_kernel.cu	…
multi_tensor_adam_kernel.cu	…
multi_tensor_apply.cuh	…
multi_tensor_l2norm_kernel.cu	…
multi_tensor_lamb_kernel.cu	…
multi_tensor_scale_kernel.cu	…
multi_tensor_sgd_kernel.cu	…
rms_layernorm_kernel.cu	[Inference/Kernel] Optimize paged attention: Refactor key cache layout (#5643)	2024-04-25 14:24:02 +08:00
scaled_masked_softmax_kernel.cu	…
scaled_upper_triang_masked_softmax_kernel.cu	…