[TVM Discuss] [Questions] TVM on windows. Setup.py problem

Are the TVM dlls (tvm.dll, topi.dll and tvm_runtime.dll) in your PATH environment var? --- [Visit Topic](https://discuss.tvm.ai/t/tvm-on-windows-setup-py-problem/6194/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click he

[TVM Discuss] [Questions] Cached Key/Function in Lower process

Perhaps it is for compiling efficiency ? In a NN Graph, there might exist many same structure relay functions (after relay Graph-Level Opt)。 So during lowering process, when meets a already lowered relay function, no need to lower again --- [Visit Topic](https://discuss.tvm.ai/t/cached

[TVM Discuss] [Questions] Do TVM runtime threads occupy CPU persistently? How to sleep them in time?

I read the code runtime/thread_pool.cc, found that enviroment var TVM_THREAD_POOL_SPIN_COUNT control the number of iterations to spin before thread sleep, it's really work in my tests. --- [Visit Topic](https://discuss.tvm.ai/t/do-tvm-runtime-threads-occupy-cpu-persistently-how-to-sleep-t

[TVM Discuss] [Questions] TVM on windows. Setup.py problem

I tried installing tvm on windows but when I try to use python setup.py install --user I get the following: (base) C:\Users\User\Desktop\Incubator-tvm\tvm\python>python setup.py install --user Traceback (most recent call last): File "setup.py", line 61, in LIB_LIST, __version__ = get_li

[TVM Discuss] [Questions] Cached Key/Function in Lower process

I noticed these terms "CCachedKey", "CCachedFunc" in lowering process in /src/relay/backend/compile_engine.cc. 1. Why is there a 'cache'? 2. What's its relationship to the lowering process? Thanks. --- [Visit Topic](https://discuss.tvm.ai/t/cached-key-function-in-lower-process/6192/1) t

[TVM Discuss] [Questions] Heterogeneous RNNs & Quantization Accuracy (an interesting case)

While post-training quantization from float32 to int8 hidden/cell states remains an open research topic, one work around we've found is to compute hidden states at higher precision on CPU rather than on the low-precision accelerator in order to reach our accuracy requirements. >From a fronte

[TVM Discuss] [Questions] How to specify target on macbook pro

OK, Thanks. I guess that on Mac, I would have to use target='llvm' and ignore the warning "Cannot find config for target=llvm, workload=('dense_nopack.x86''. --- [Visit Topic](https://discuss.tvm.ai/t/how-to-specify-target-on-macbook-pro/6182/3) to respond. You are receiving this because

[TVM Discuss] [Questions] CUDA FP16 example

Is converting a model to FP16 with target = "cuda" supported? If so, is there an example pass I could look at to convert my model? cc @vinx13 @Hzfengsy Thanks! --- [Visit Topic](https://discuss.tvm.ai/t/cuda-fp16-example/6190/1) to respond. You are receiving this because you enabled ma

[TVM Discuss] [Questions] [RUNTIME] Can tvm call TensorRT as third-party runtime engine?

TRT integration is now working but only on the [AWS forked repo](https://github.com/neo-ai/tvm). @trevor-m is working hard to make it upstream. Since the external codegen infra still requires some improvements, it might take some more time. --- [Visit Topic](https://discuss.tvm.ai/t/runt

[TVM Discuss] [Questions] How to specify target on macbook pro

Mac hasn't used nvidia graphic card for a LONG time (>5 years?), which means your laptop doesn't support a CUDA-enabled device. You'll need a new platform to try cuda. --- [Visit Topic](https://discuss.tvm.ai/t/how-to-specify-target-on-macbook-pro/6182/2) to respond. You are receiving t

[TVM Discuss] [Questions] NDK error when compiling for ARM

I met the same problem, anyone solved it? --- [Visit Topic](https://discuss.tvm.ai/t/ndk-error-when-compiling-for-arm/670/4) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/3

[TVM Discuss] [Questions] [RUNTIME] Can tvm call TensorRT as third-party runtime engine?

Hi! Whats the current status on this? Thanks! --- [Visit Topic](https://discuss.tvm.ai/t/runtime-can-tvm-call-tensorrt-as-third-party-runtime-engine/5074/4) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://d

[TVM Discuss] [Questions] How CUDA kernel is launched in TVM stack

Hi: I am investigating the capability of TVM primitives (CUDA backend). I take CUTLASS as a baseline of highly-optimized CUDA library. I think most of optimization techniques used in CUTLASS like tiling, shared_mem management are supported by TVM primitives. Streaming is also an important

[TVM Discuss] [Questions] How CUDA kernel is launched in TVM stack

I don't know or think if we are exposing CUDA stream abstraction to python frontend. We typically don't care about cuda stream (we don't support any concurrency at runtime). What is your use case? --- [Visit Topic](https://discuss.tvm.ai/t/how-cuda-kernel-is-launched-in-tvm-stack/6167/7)

[TVM Discuss] [Questions] How CUDA kernel is launched in TVM stack

Hi: Thanks for you answer. I will check autotvm to see how it tunes grid/block. Because based on experience, grid/block dims will affect performance. And another question is that, I see there is arg for **cuda stream** ``` CUstream strm = static_cast(CUDAThreadEntry::ThreadLocal()->stream);