Example of running inference on a int8 quantized model? [Uncategorized] (2)
[Tensor Expression] add hardware specific schedule [Development] (16)
How to emit llvm IRs from a Relay graph module? [Questions] (3)
Model can Import by NNVM but failed on Relay [Uncategorized] (5)
Android RPC failed [Questions] (2)
Curve Feature (Relation Feature) [Questions] (6)
[SOLVED] C++ inference test app doesn't work correctly [Application] (16)
[Solved] Build failure in jvmpkg [Development] (4)
Changes due to Apache Incubation? [Development] (2)
Error "direct host side access to device memory is detected in ... , did you forget to bind?" when compile a onnx model with target cuda ( 2 ) [Questions] (22)
[SOLVED]Adding tvm4j to a bazel build [Uncategorized] (4)
The demo of android (adroid_deploy) run with crash [Application] (9)
How to use 8-kernel CPU to run TVM [Questions] (5)
AutoTVM test samples [Questions] (5)
Confused: TVM vs TF, performance compare [Questions] (4)
Failed to convert gluoncv yolov3 into tvm [Questions] (3)
[VTA] Questions about VTA packed format [Questions] (7)
How to build tvm with openblas on macOS [Questions] (2)
New Committer: @kazum [Announcement] (1)
Model performance is much slower on Android Device using Java API, ComparedToRunEvaluator [Uncategorized] (3)
Print the function code from lib [Questions] (3)
Deploying a TVM model with LLC options [Uncategorized] (3)
[VTA&TVM] Questions after investigating resnet.py tutorial [Questions] (6)
How to build tvm as static library and inference using c++? [Questions] (15)
can't deploy ssd with gluoncv [Questions] (9)
[solved]Compilation error running tune_nnvm_arm.py [Questions] (1)
INT8 quantization vectorize sum problem [Questions] (3)
[pipeline] Did TVM support base64 or iostream input instead of ndarray? [Questions] (5)
Relay Alter OP Layout Pass Regression [Uncategorized] (10)
Binarize a NN for raspberry PI [Questions] (4)