* [feature] add cudagraph support
* modify code to pass the cuda_all_reduce test
* modify rope op
* support rmsnorm
* add fp16 support to silu cuda op
* fix bugs in rmsnorm op
* uncomment simplify in onnx.py
---------
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
* feat: SqueezeOp lift the dependency of onnx infershape.
* feat: UnsqueezeOp lift the dependency of onnx infershape.
* feat: lift the dependency of onnx infershape
* fix: fix Makefile off nccl
* - add layernorm kernel
* success:add layernorm kernel and test
* fix: remove unusalble comments
* fix: modify code as reviewer suggested
* debug,modified .cu and test
* optional bias support
* overloading function
* fix bug after merging; remove time constrain in conv test
---------
Co-authored-by: kilinchange <kilinchange@163.com>
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
* Add reduceSum op and kernel
* fix merge and format
* Reduce: reuse cat macro, add doc string
---------
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
* feat: support dynamic tensor part1
* feat: support dynamic-tensor part2
* feat: support dynamic tensor part 3
* fix: fix some ..
* - add kvcache example
* feat: support concat to identity kernel
* add a simple mempory pool for allocator
* fix: rebase to master
* fix bug after merging
* - remove outdated script
* fix: fix as review
---------
Co-authored-by: kilinchange <kilinchange@163.com>
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
* [feature] add fused attention_kvcache operator support
* add test to attention_kvcache op
* Add space line at EOF
---------
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
* fix Slice
* change default rounds of timeit to 10 to reduce time
* fix slice with large ends
* Reshape support Int64
* support position_ids as input
* skip last MatMul in Llama
* skip infer_shapes to parse large model
* update launch.py
* fix split_concat_kernel
* print more message in launch.py
* Reshape supports both Int32 and Int64
* try infer_shapes and warn about failure
* fix format
---------
Co-authored-by: whjthu <haojie0429@gmail.com>
* Add GatherElements op and cuda kernel
* fix format
* remove print
* remove unused var
* fix spacing
* fix format
---------
Co-authored-by: panzezhong@qiyuanlab.com <panzezhong@zezhongpan>
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
* add ceil mode for pooling
* do not print debug info for allocator by default
* fix test bugs after introducing pooling ceil mode
* fix onnx import bug
* add cmake bits about NCCL
* move example to examples/NNmodel
* impl NCCL communicator
* add comm related function to Runtime
* export runtime interface
* add launch.py
* use unique name to distingush the the NCCL ID file
* add timeout to communicator init
* expose communicator obj from runtime obj, add unit test for nccl communicator
* reformat files
* Add allReduce operator and cuda nccl allReduce kernel
* impl model parallel for resnet
* add allGather nccl kernel and operator
* Add allreduce allgather operator tests, change allgather kernel to output list of tensor, fix shape infer, handle nullptr output
* fix format of onnx.py
* use concat following AllGather
* get tensor parallel for resnet
* fix format of graph_handler.cc
* change BUILD_DIST default to OFF
* polish code of communicator
* update .gitignore
* export min/max to python
* fix MatMul
* modify launch.py to run opt
* hack to treat ReduceSum as AllReduceSum
* throw exception in cuda error
* fix parallel_opt.py
* improve the error prompt and cuda error check
* fix GatherObj::GatherObj member init
* fix size calculation for scalar (rank = 0) tensor
* MatMul supports bias
* fix add bias for row parallel gemm
* add --gen_std to launch.py
* fix AllReduceNCCL
* update launch.py
* less log
* update parallel_opt
* update launch.py
* add __eq__ for Placement sub-classes
* less benchmark run
* fix placement infer for matmul
* fix vacabuary size
* fix Exception
* Add shard tensor with group to support gpt2
* Add find successor function to find split op at different depth
* recover CommunicatorObj
* improve error mesasge
* optimize parallel_opt.py
* optimize launch.py
* recover docs for all_reduce and all_gather
* Fix API
* fix format
---------
Co-authored-by: panzezhong <panzezhong@qiyuanlab.com>
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
* add cmake bits about NCCL
* move example to examples/NNmodel
* impl NCCL communicator
* add comm related function to Runtime
* export runtime interface
* add launch.py
* use unique name to distingush the the NCCL ID file
* add timeout to communicator init
* expose communicator obj from runtime obj, add unit test for nccl communicator
* reformat files
* Add allReduce operator and cuda nccl allReduce kernel
* impl model parallel for resnet
* add allGather nccl kernel and operator
* Add allreduce allgather operator tests, change allgather kernel to output list of tensor, fix shape infer, handle nullptr output
* fix format of onnx.py
* use concat following AllGather
* get tensor parallel for resnet
* fix format of graph_handler.cc
* change BUILD_DIST default to OFF
* polish code of communicator
* update .gitignore
* Add broadcast operator and cuda kernel
* Add comments for operators
* remove const of class member
* move communicator to CudaRuntimeObj
* Add an empty line at EOF.
---------
Co-authored-by: panzezhong <panzezhong@qiyuanlab.com>
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
* feat: support to sqrt op
* feat: support to erf op
* feat: support to expand op
* feat: support to where op
* fix: gather op index can be int64_t(hard coding)
* fix: some wrong use
* style: fix the format style
* test: add test for change op
* fix: rebase to master
* fix: fix matmul b compute wrong
* add expand and where kernel
* Add int64 support for cuda gather kernel
* add test_where.cc
* add "expand.(cu/cc,test,cuda),modified where.cu"
* Separate initialization of datatypes to avoid compile error
* modify where.(cu/cc/h,test), expand and clip
* Format fix
* Format fix
---------
Co-authored-by: xgqdut2016 <kenan_gewei@163.com>
Co-authored-by: panzezhong <panzezhong@qiyuanlab.com>
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
* impl sqrt on CUDA
fix parser of Gather and ReduceMean
* fix test_gather
* fix test_cuda_gather
* impl sqrt cpu and add sqrt to test_cuda_unary
* cuda_unary supports arbitary shapes
* fix SplitOp with dim=-1
* fix SplitOp with dim=-1
* feat: support mixed dtype
* feat: support cast op
* test: add test for cast op
* feat: support datatype BFloat16
* feat: support data convert fp32 <-> bfp16
* fix: fix all op's infershape func
* fix as review comment
reconfig: connections among op and tensor now is managered by GraphObj .
add some comments
merge from master
merge from master
ADD: sub graph replacement
reconfig inputs of op resize, due to the check of operator inputs.
ResizeObj::clone
clang format
fix some and add test for multi-output.
replacement support multi-inputs and multi-outputs.
add clone for all operators
add replaceSubGraph addSubGraph
remove extra code
add more test
remove extra print
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
fix review
change Device::MKL to Device::INTELCPU
fix mkl linkage
fix errors according to merge from master
now can call mkl backend
fix softmax/flatten with axis from onnx.
modify README.md
fix memory refree
add env_lotus_intelcpu.sh
fix compile
merge from branch cpu_backend
fix something add gather
fix something
FIX: directory rename from "mkl" to "intelcpu"
ADD: use oneMKL dpcpp interface to implement matmul kernel.
ADD: add dpcpp as compiler for mkl, and fix warnings for clang compiling.
add dpcpp kernel for pow.
ADD: mkl kernel for pad.
ADD: slice mkl kernel.
ADD: reshape/flatten/identity mkl kernel.
ADD: split mkl kernel.
fix compile error
FIX: fix flattenObj with axis.
ADD reduce_mean mkl kernel.
Add concat mkl kernel.
bathNorm for mkl kernel.
sigmoid mkl kernel.
ADD：add mkl kernel for pooling
add more tests for softmax
Now softmax cuda kernel supports any axises.
mkl kernel for softmax
softmax
add axis to softmax operator
add mkl kernel for abs tanh
ADD: relu kernel for mkl
fix binary mkl primitives.
add mkl kernel for binary operators
fix compiler error
move stream to runtime
clang format
add MemoryFormat for tensorObj.
use post_ops for fused conv/deconv
Distinguish mkl op_timer from cuda op timer.
add act optype to conv and deconv
add operator timer
add mkl kernel for convTransposed
minor fix for group conv
do not use cblas_sgemm_batch
CpuRuntimeObj->NativeCpuRuntimeObj
add matmul op for mkl
* move memory format transformation to TensorObj
clang format
add MemoryFormat for tensorObj.
use post_ops for fused conv/deconv
Distinguish mkl op_timer from cuda op timer.
add act optype to conv and deconv
add operator timer
add mkl kernel for convTransposed
minor fix for group conv
do not use cblas_sgemm_batch
CpuRuntimeObj->NativeCpuRuntimeObj
add matmul op for mkl
* fix: fix bugs when rebasing from master
fix: fix bugs when rebasing from master
* fix: update api after rebasing
* fix: fix format; fix onnx import
* fix: fix clang-format
* [fix] fix conv_transpose test
* [fix] use stronger test case for transposed conv
* [fix] remove tensor memory format; fix mkl transpose conv
* [fix] add FIXME tag for op_timer python api
---------
Co-authored-by: whjthu <haojie0429@gmail.com>
ADD: resize operator and cuda kernel,support nearest/linear coef.
fix some
fix tests
add more tests for linear mode.
add linear coef mode.
add scales
add tests
fix tests.
add notLarger notSmaller
fix
add test
ADD:resize operator and cuda kernel
fix numInputs of batchNorm, add new line in file ending.
ADD: batch norm operator and cuda kernel.
add training
remove comments.
fix compile error.
add batch norm operator and cuda kernel.
xiaonans
Derui Yang