[Apache TVM Discuss] [Application] Naming convention for start_name and stop_name

2020-11-02 Thread sachacon via Apache TVM Discuss
Hi @wltz did you ever resolve this "assert int(dshape[1]) % cfactor == 0" error? I'm encountering the same issue in my code as well. --- [Visit Topic](https://discuss.tvm.apache.org/t/naming-convention-for-start-name-and-stop-name/5304/2) to respond. You are receiving this because you en

[Apache TVM Discuss] [Questions] Is there a quick method to translate pure-c-code/IR in cfiles to TVM/HalideIR AST?

2020-11-02 Thread Shawn Zhuang via Apache TVM Discuss
Is there a quick method to translate pure-c-code/IR in cfiles to TVM/HalideIR AST? --- [Visit Topic](https://discuss.tvm.apache.org/t/is-there-a-quick-method-to-translate-pure-c-code-ir-in-cfiles-to-tvm-halideir-ast/8353/1) to respond. You are receiving this because you enabled mailing l

[Apache TVM Discuss] [Questions] Change PYNQ board frequency with current VTA version?

2020-11-02 Thread ffffc via Apache TVM Discuss
You can find it in tvm\3rdparty\vta-hw\config\pkg_config.py --- [Visit Topic](https://discuss.tvm.apache.org/t/change-pynq-board-frequency-with-current-vta-version/8279/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click

[Apache TVM Discuss] [Questions] How to match the pattern of a function in Relay?

2020-11-02 Thread moderato via Apache TVM Discuss
Thanks! I'll try that after I fix up some of the bugs I'm having. --- [Visit Topic](https://discuss.tvm.apache.org/t/how-to-match-the-pattern-of-a-function-in-relay/8283/19) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click

[Apache TVM Discuss] [Questions] Why not implement bitserial_* op in GPU

2020-11-02 Thread lin bin via Apache TVM Discuss
I used the bitserial_conv2d_nchw and bitserial_dense in x86, but I found such op didn't support GPU platform. Why not implement it in GPU? Is it hard to support such thing? --- [Visit Topic](https://discuss.tvm.apache.org/t/why-not-implement-bitserial-op-in-gpu/8352/1) to respond. You a