Nothing @myuniqueusername, I am also are waiting for reply. Please let me know
if you find something.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/cannot-squeeze-axis-with-dimension-not-equal-to-1/8370/3)
to respond.
You are receiving this because you enabled mailing list mode.
To
Did you mean the number of cycles for a single GEMM instruction? AKAIK, it
depends on the implementation, as it for Chisel-based implementation, a single
GEMM instruction takes 4 cycles to complete, since there are stages in the
design that prepare the data stream for such execution.
---
Before start working on actual FPGA, we could evaluate with TSIM
(cycle-accurate simulation) in TVM; For experiments with vision models, please
refer to [ Deploy Pretrained Vision Model from MxNet on
VTA](https://tvm.apache.org/docs/vta/tutorials/frontend/deploy_classification.html?highlight=t
I want to deploy object detection on ZYNQ104, but I am a fresh man on machine
learning and FPGA, can I use emulator to do it? I do not have an FPGA yet, but
I want to do experiment to compare it.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/deploy-object-detection-on-gpu-and-fpga/85
I would like to know if there is a way to deploy the TVM module to a cluster of
hardware devices for performance gain. Example multiple CPUs/GPUs. It can be a
homogeneous cluster.
---
[Visit Topic](https://discuss.tvm.apache.org/t/deploy-model-on-cluster/8516/1)
to respond.
You are recei
https://github.com/apache/tvm/pull/6968/files
---
[Visit
Topic](https://discuss.tvm.apache.org/t/ci-c-standard-for-the-tvm-project/8508/5)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.apache.
I was trying to speed up my model running on Android device, but failed on the
"Evaluating" step.
Firstly, I tested the
[tune_relay_arm.py](https://tvm.apache.org/docs/tutorials/autotvm/tune_relay_arm.html#sphx-glr-tutorials-autotvm-tune-relay-arm-py)
scripts following the instruction. (The v
