Development


About the Development category (1)
Request for invite to the slack channel (5)
[RELAY] Logging disabled for printing TVM IR (2)
TVM support int8 quantize on arm-cpu? (1)
Where vs Select operators in the Tensorflow frontend (1)
[AutoTVM] How can I see the domain-specific features in the Statistical Cost Model (1)
Docker build fails for while building image from Dockerfile.demo_cpu (1)
NNVM / Relay compiler doesn't support tensors. Crashes with "AttributeError: 'Tensor' object has no attribute 'node'" (3)
Request for invite to the developer slack channel (2)
Missing tflite operators (7)
Quantization broken due to PR #3135 (8)
Explore Optimizations for Concat (17)
What is the long-term development of TVM? I have some puzzles (2)
[solved][Relay] Broken case of type infer (3)
[ONNX] Missing and outdated operators (1)
[Relay] Higher order AD broken in some cases (8)
Who is interested in running MLPerf on VTA? (3)
Getting started with the VTA Chisel backend (19)
TSIM Cycle Measurement Question for Parallel Module (3)
[Discuss] Modify PassUpDomain for efficiency (3)
How to support tf.TensorArray() (4)
[RFC] Simplifying Module System (4)
[Relay][PrettyPrinter] Handling nested Let in Let-binding value (1)
RPC context is not identifying gpu device (1)
[Discuss] Should the Relay module include the prelude by default? (1)
Should we use PureExtern for some TVM ops? (12)
How to create a new operator in TVM (1)
From_onnx conversion issue with MatMul+Add (3)
OpenCL AutoTVM questions (9)
What float-abi and fpu should be used for Raspberry Pi ARMv7l model so file? (5)