Topic Replies Activity
[COMMUNITY] TVM Conference 2019

Dear TVM Community: As many of you already know. We are organizing another annual conference for the TVM community. We just posted a preliminary program and opened registrations: https://sampl.cs.washington.edu/tvmconf/ …

2 October 24, 2019
Welcome to TVM Community 2 June 3, 2019
[USABILITY IDEA] Create a command line compiler that would perform common build tasks out of the box 5 December 15, 2019
Can I write relay directly and compile it to llvm IR? 1 December 15, 2019
TVM for edge computing
RFC
2 December 15, 2019
The section "Load a test image" of the Tutorial is wrong: it normalizes input to 2 which is usually not the case 1 December 15, 2019
Understanding the constraints of bind and compute_at 1 December 14, 2019
Understanding TVM's scheduling primitives 3 December 14, 2019
relay.build fails: module 'tvm.codegen' has no attribute 'llvm_version_major' 2 December 14, 2019
Shall we print nothing when there is no side effect in Evaluate for CodeGenC? 3 December 14, 2019
Import tvm returns Runtime error (can't find libtvm.so) when using docker demo-cpu image 2 December 13, 2019
CodeGen aware of model weights? 1 December 13, 2019
[DISCUSS] Adding a PyTorch Frontend
RFC
17 December 13, 2019
Moving up to Tensorflow 1.15.0 and Tflite 1.15.0 and other Framework upgrades 1 December 13, 2019
[VTA] Issue with TSIM based simulation of resnet18 inference on VTA 14 December 13, 2019
Missing expr and stmt in c codegen? 2 December 13, 2019
The is_const function for Expr is too weak? 1 December 13, 2019
[VTA} Error when running autotune tutorial 6 December 13, 2019
Difference of RPC Connection on PYNQ-Z1, VTA 3 December 13, 2019
Auto-tuning with Relay: RPC Tracker Error 4 December 13, 2019
Can TVM now support Dynamic Shaped Tensors? 5 December 13, 2019
Autotvm can not load the NHWC model? how should i do? 1 December 13, 2019
Onnx fronend test failure by segmentation fault 3 December 13, 2019
Runtime GetFunction(...): How to differentiate tensors in TVMArgs? 1 December 13, 2019
Block Diagram for Chisel VTA 7 December 12, 2019
[VTA] Scalability for data center FPGAs 10 December 12, 2019
Dense layers do not quantize from float32 to int8 in relay 5 December 12, 2019
[VTA][Chisel] Redundancy of having 32-bit Accumulator matrix in GEMM
RFC
3 December 12, 2019
Can I deploy multiple VTAs and run those on single PYNQ board? 3 December 12, 2019
The correct the target for CPU? 1 December 12, 2019