You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 
limingqi107 825aca33c2 add tensor copy kernel on GPU/CPU 4 years ago
..
arrays add tensor copy kernel on GPU/CPU 4 years ago
control code check for ops 4 years ago
cuda_impl support_bool 4 years ago
custom optimizes the kernel error description of GPU about tile,topk,transpose etc. 4 years ago
data fix getnext timeout or coredump 4 years ago
debug optimizes the kernel error description of GPU about tile,topk,transpose etc. 4 years ago
environ environ bug fix in control flow 4 years ago
math roll back random normal op 4 years ago
nccl !28300 optimizes the kernel error description of GPU about tile,topk,transpose etc. 4 years ago
nn psroipooling 4 years ago
other optimizes the kernel error description of GPU about tile,topk,transpose etc. 4 years ago
quant !28300 optimizes the kernel error description of GPU about tile,topk,transpose etc. 4 years ago
random optimizes the kernel error description of GPU about FakeLearnedScaleQuantPerChannelGrad etc. 4 years ago
rl optimizes the kernel error description of GPU about FakeLearnedScaleQuantPerChannelGrad etc. 4 years ago
sponge fix ops 4 years ago
trt optimizes the kernel error description of GPU about FakeLearnedScaleQuantPerChannelGrad etc. 4 years ago
gpu_kernel.cc fix issue#I3ARG6 5 years ago
gpu_kernel.h Put the kernel graph cut according to the partial in the same group. 4 years ago
gpu_kernel_factory.cc refine log of kernel select 4 years ago
gpu_kernel_factory.h clean up the static alarms of the second batch of operator groups 4 years ago
kernel_constants.h add cholesky, cho_factor primitive and backend gpu implements 4 years ago