Messages by Thread
-
-
[Apache TVM Discuss] [Questions] [TIR/Relay] why tvm.tir api generates relay IR
Teng HUANG via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Model graph size doubling after partitioning for arm compute library
bolt via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Tiled tensors for external (python) functions and TIR == te.extern?
cronos via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Passing a tuple to a packed func?
cronos via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] InferCorrectLayout
Knight3 via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] How to dump IRs for each pass when building a model
Teng HUANG via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] How to build libtvm_runtime.so for armeabi-v7a or arm64-v8a?
ERROR via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Cannot export static android system-lib model
ERROR via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] TVM Optimizations for edge computing
Abid Malik via Apache TVM Discuss
-
[Apache TVM Discuss] [Application] [µTVM] Static Runtime Code Generator
Turing42 via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] On the JIT Runtime heterogeneous execution for VTA
Jorge Sierra via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Relay VM newbie: Porting Relay VM question
zsteve6927 via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Index_put operator in Relay
Alexander Pivovarov via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] How to extract a relay function when doing partitioning with relay pattern?
jmatai via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] TVM deploy a C++ example
sara via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Measuring uTVM inference time
Sky via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Can we generate assembly code that tensor dimensions are not fixed?
Johnson Lu via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Redundant Transpose Operations in Relay from pyTorch
Hongsong Li0728 via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Deploy object detection on GPU and FPGA
Alex via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Deploy model on cluster
Sky via Apache TVM Discuss
-
[Apache TVM Discuss] [Application] Auto tuning self onnx model with Android-rpc and failed on the "Evaluating" step
pminimd via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Nn.dense attribute question
Chris Gyurgyik via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] [CI] C++ standard for the TVM project
Manupa Karunaratne via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] MergeComposite Error when defining custom pattern
Limenghao via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] TVM for ARM CPU - Android rpc apk
pminimd via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] TVM Auto-tune: Reducing the number of tasks
Andrew_KR via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] [VTA] Generate a new bitstream for other targets and clk-frequency
Yangjun Li via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] [VTA] Are VTA testbench scripts fully rely on autotvm?
Kazuei HIRONAKA via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Auto-tune finished, but Build error occurs for my own onnx model
Eye via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] How can I get output name from graph runtime
ERROR via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] What Relay op would allow for splitting a tensor along an axis?
Steven S. Lyubomirsky via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Use all cores in a big.LITTLE architecture
Wheest via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Cannot run the sample code , With message: "Check failed: oshape_sum == data_shape_sum "
zhaozilong via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] [VTA] issue with TLPP design
Rahul shrivastava via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] ARM time evaluator with cpu flush cache
Bernhard Klein via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] [VTA] Non-linear op support for VTA?
keai007 via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] [VTA] dens layer support
Thomas Rocznik via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] [VTA] GEMM cycle count
Thomas Rocznik via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] About document version
ProfXGiter via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Multiple right hand sides for reduction
Chris Nuernberger via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Cannot run the sample code ,"Check failed: oshape_sum == data_shape_sum "
zhaozilong via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] How to set address in android_rpc APP when host is VMware ubuntu?
Turbo Liu via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Crttest failed, no rules to make the target "crttest"
zhaozilong via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Run the tutourials file failed cuda is not enable
piaodangdang via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] How to add new scheduler in auto-tvm
haiou via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] How to use Arm compute library with android RPC?
Albin via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] What't the arguments order of TVM generated cuda kernel?
luchangli via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Why the mobilenet workload result is all 0.001
forrest via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Doubt in loadbuffer parameters in VTA matrix multiplication tutorial
Rahul shrivastava via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Difference with ONNX
Jhagege via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] How to let cache_write() compute at "k" axis in GEMM?
Zhuwenxi via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] How to create PackedFunc manually?
JC Li via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] How to get host code or blockIdx, threadIdx of GPU op
luchangli via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] [VM] The performance degradation of VM runtime and Dynamic Shape support compared to Graph Runtime
Chao Liu via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Removing intermediate tensors/replacing to temporary variable
kwmaeng via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Print IRModule without meta data
Takato Yamada via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] How to replace the default code for nn.conv2d at the target llvm
Giuseppe Rossini via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] List of CUDA targets
Abelardo López-Lagunas via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Where does the layout transform of each op happen during alter_op_layout pass?
moderato via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] TVM terms: relay, topi, tir, te
Christoph Gerum via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Virtual threading scheduling primitive
Heart1998 via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Cannot squeeze axis with dimension not equal to 1
Ravish via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] [Quantization] How to add new quantization method for TVM
fredjon via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] How can I test the performance of a single operator?
haozech via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] After auto tuning, what other optimizations based on tir will be done?
sqchao via Apache TVM Discuss
-
[Apache TVM Discuss] [Application] Naming convention for start_name and stop_name
sachacon via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Is there a quick method to translate pure-c-code/IR in cfiles to TVM/HalideIR AST?
Shawn Zhuang via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Why not implement bitserial_* op in GPU
lin bin via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] TVM int8 graph Optimization relu problem
dingyongchao via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Tutorial, "How to optimize matmul with Auto TensorCore CodeGen", cannot work on my machien
Steven via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Issues with Autotuning a Convolutional Network for VTA Simulator
keai007 via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] ReduceNode in TIR
Xqdan via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Autotuning for conv2d_nchw and dense_small_batch
Andrew_KR via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] [AutoTVM] How to set up OpenCL when tuning Mali GPU?
Wei Wei via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Can we dump every op's output?
wda via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Partial neural network evaluation for streaming data
Rsaymore via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] How to modify and add an operator in pytorch frontend
tang Iverson via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] When windows10 run tvm(cuda10.2 llvm9.0),run these code,it will return this error,anyone can tell me what happen?
wangbingjia via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Does autotvm support 3D networks for cpu and gpu?
aiblackman via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] [AutoTuning] How to debug when all trials are failing on GPU
jeremyj via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Relay cannot compile while_loop
Hao Luo via Apache TVM Discuss
-
[Apache TVM Discuss] [Questions] Understanding TVM/Relay's PartitionGraph()(mod) function
jmatai via Apache TVM Discuss