You are viewing a plain text version of this content. The canonical link for it is here.
- [Apache TVM Discuss] [Questions] Graph optimization not exist in GPU? - posted by aleczhanshi via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/01 01:31:24 UTC, 10 replies.
- [Apache TVM Discuss] [Questions] Topi.sqrt and other functions throwing an error in opencl target - posted by Akhil via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/01 03:06:49 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] How to view Host code generated for opencl target in TVM - posted by Akhil via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/01 03:16:16 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Profiling a TVM run on CPU - posted by Aakah via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/01 09:06:03 UTC, 1 replies.
- [Apache TVM Discuss] [Questions] TVM CUDA warp-level sync? - posted by Tristan Konolige via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/01 16:34:07 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] C++ APIs of Ansor auto-scheduler - posted by Hecmay via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/01 20:12:46 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Support for pre-quantized model int8/uint8 conversion - posted by JoeyChou via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/01 21:48:01 UTC, 4 replies.
- [Apache TVM Discuss] [Questions] Cannot find config for target=llvm -keys=cpu - posted by aleczhanshi via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/02 10:50:01 UTC, 2 replies.
- [Apache TVM Discuss] [Questions] [VTA][Pynq][Chisel] Creating bitstream from Chisel source instead of HLS for Pynq-Z1 - posted by Minisparrow via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/04 03:10:15 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Matrix multiplication example for Cuda - posted by Le Xu via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/05 05:34:49 UTC, 1 replies.
- [Apache TVM Discuss] [Questions] [VTA] Deploy Pretrained Vision Model from Pytorch on VTA - posted by isong via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/06 09:27:24 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Error: Class referenced in the manifest, org.apache.tvm.tvmrpc.RPCWatchdogService, was not found in the project or the libraries - posted by Tengfei han via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/06 10:57:20 UTC, 1 replies.
- [Apache TVM Discuss] [Questions] Training models; current state - posted by Julian via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/07 10:46:33 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Creating subgraphs from a Tensor Expression - posted by Matt Barrett via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/07 15:46:50 UTC, 3 replies.
- [Apache TVM Discuss] [Questions] [iOS- Auto Tvm] Auto Tuning was not happening for iOS metal target - posted by Dileep via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/08 04:52:56 UTC, 3 replies.
- [Apache TVM Discuss] [Questions] What is the best approach to convert a pytorch model to TVM? - posted by Nauman007 via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/08 18:22:12 UTC, 3 replies.
- [Apache TVM Discuss] [Questions] Can we use TVM as JIT compiler? - posted by Giuseppe Rossini via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/08 23:03:37 UTC, 8 replies.
- [Apache TVM Discuss] [Questions] Where to find Generated RTL Files - posted by sachacon via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/09 18:22:38 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] FoldConstant doesn't fold two consecutive add - posted by JoeyChou via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/09 19:01:00 UTC, 2 replies.
- [Apache TVM Discuss] [Questions] Whether TVM has batch optimization - posted by Shengxi Li via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/12 02:33:39 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Add new backend - posted by Minisparrow via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/12 07:31:32 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] How to verify the correctness of different schedule and tile size in autotvm? - posted by HaoyuChi via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/12 08:25:57 UTC, 1 replies.
- [Apache TVM Discuss] [Questions] Prefetch shared memory to registers - posted by Zhiying Xu via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/12 09:24:04 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Can the TVM stack target RISC-V? - posted by Davide Giri via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/12 22:04:22 UTC, 2 replies.
- [Apache TVM Discuss] [Questions] Auto-scheduling for lstm operator - posted by jialipang via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/13 02:58:37 UTC, 7 replies.
- [Apache TVM Discuss] [Questions] Dose TVM only support dense operation? - posted by yufeng via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/13 04:55:22 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] How to I use prefetch with GPU codegen - posted by Zhiying Xu via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/13 05:27:25 UTC, 1 replies.
- [Apache TVM Discuss] [Application] Compile Keras Neural Network Models - posted by rahul1 via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/13 13:41:32 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Compile examples in frontend - posted by rahul1 via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/13 15:05:40 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Dose TVM only support mkldnn dense operation? - posted by Tristan Konolige via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/13 17:36:42 UTC, 2 replies.
- [Apache TVM Discuss] [Questions] Compile to adreno GPU - posted by vadim dit via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/14 07:54:11 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Why does GetUniqueName replace "." with "_"? - posted by stuart_yang via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/14 13:22:10 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Get_num_inputs returns empty - posted by Chigo via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/15 10:43:20 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] [VTA] How can I calculate VTA GOPs? - posted by Hagoon via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/15 19:39:28 UTC, 1 replies.
- [Apache TVM Discuss] [Questions] TVMArrayAlloc BUG? - posted by Zhang11344035 via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/16 03:39:29 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Erroring in IRModule update function - posted by Steve via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/17 00:11:20 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] [ Question ] Is Batch Normalization necessary when inference? - posted by kyunghawn choi via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/17 04:14:52 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Error building android_rpc - posted by Beom Woo Kang via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/18 07:25:18 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] How dose TVM elimitate calls of conv weights layout_transform? - posted by Jason via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/19 09:38:21 UTC, 4 replies.
- [Apache TVM Discuss] [Questions] Is multi-threading supported when TVM target SGX? - posted by fabian lee via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/20 08:51:57 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Is there a better way to see stmt when we write a tvm pass? - posted by Minisparrow via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/20 09:37:23 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] About Configspace in autotvm - posted by Suhas via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/20 10:20:44 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Is Module thread-safe? - posted by xiandi via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/20 13:33:48 UTC, 2 replies.
- [Apache TVM Discuss] [Questions] Do we have to identify tvm.nd.array context? - posted by SunWook Jung via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/20 17:11:57 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] [CUDA]Got Error: CUDA ERROR LAUNCH OUT OF RESOURCES - posted by Cuiqing Li via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/20 19:45:48 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Why stop quantize after first ``nn.global_avg_pool2d`` - posted by Eye via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/21 02:50:51 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Why am I getting ' Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload= - posted by Cheng Zhang via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/22 02:50:11 UTC, 2 replies.
- [Apache TVM Discuss] [Questions] nnvm._base.NNVMError: Error in operator 316: [10:41:59] src/top/nn/nn.cc:201: Check failed: (size_t)param.axis < dshape.Size() - posted by Ninurs via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/22 03:30:41 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] How to use Relay Control Flow? - posted by wwwwcu via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/22 05:21:30 UTC, 4 replies.
- [Apache TVM Discuss] [Questions] Where to find device.py - posted by Qelk123 via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/22 06:28:10 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] CPU cycle during inference? - posted by Aakah via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/22 17:49:40 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] run example for tvm complie tensorflow model, It's very slow - posted by jieson via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/23 00:29:54 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] How to modify and add new operators - posted by tang Iverson via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/23 02:22:26 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Doxygen API lacks classes of namespace "tvm::codegen"? - posted by Johnson9009 via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/23 03:39:36 UTC, 1 replies.
- [Apache TVM Discuss] [Questions] [Relay] CUDA_ERROR_INVALID_VALUE occurs when testing conv2d_grad - posted by Cuiqing Li via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/23 08:31:39 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] How to use target.list_tags()? - posted by Aakah via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/23 13:14:53 UTC, 4 replies.
- [Apache TVM Discuss] [Questions] Bring your own codegen and C Runtime - posted by Ajay J via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/23 14:44:27 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] TVM iOS deployment - posted by kindlehe via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/23 17:05:11 UTC, 0 replies.
- [Apache TVM Discuss] [Application] Your micro_tflite.ipynb doesn't work: import tvm issue in Colab - posted by danilopau via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/23 17:58:17 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] I can't find directory'device' in tvm/micro - posted by Qelk123 via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/24 06:28:39 UTC, 1 replies.
- [Apache TVM Discuss] [Questions] Is sparse kernel supported in the tensor expression language? - posted by kwmaeng via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/24 21:58:28 UTC, 2 replies.
- [Apache TVM Discuss] [Questions] Graph_plan_memory doesn't support nested tuples? - posted by masahi via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/25 23:36:01 UTC, 8 replies.
- [Apache TVM Discuss] [Questions] Change PYNQ board frequency with current VTA version? - posted by sachacon via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/26 00:22:10 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] How to detect the pattern of a function? - posted by moderato via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/26 08:25:51 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Cloning a NN model - posted by M1k3 via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/26 19:08:44 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Understanding TVM/Relay's PartitionGraph()(mod) function - posted by jmatai via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/26 20:08:55 UTC, 7 replies.
- [Apache TVM Discuss] [Questions] Relay cannot compile while_loop - posted by Hao Luo via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/27 02:45:41 UTC, 2 replies.
- [Apache TVM Discuss] [Questions] How to match the pattern of a function in Relay? - posted by "Cody H. Yu via Apache TVM Discuss" <no...@discuss.tvm.ai> on 2020/10/27 04:21:17 UTC, 16 replies.
- [Apache TVM Discuss] [Questions] [AutoTuning] How to debug when all trials are failing on GPU - posted by jeremyj via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/27 06:56:11 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Does autotvm support 3D networks for cpu and gpu? - posted by aiblackman via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/27 11:20:08 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] When windows10 run tvm(cuda10.2 llvm9.0),run these code,it will return this error,anyone can tell me what happen? - posted by wangbingjia via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/27 16:18:08 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] How to modify and add an operator in pytorch frontend - posted by tang Iverson via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/28 02:37:19 UTC, 1 replies.
- [Apache TVM Discuss] [Questions] Partial neural network evaluation for streaming data - posted by Rsaymore via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/28 21:26:10 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Can we dump every op's output? - posted by wda via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/29 07:01:47 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] [AutoTVM] How to set up OpenCL when tuning Mali GPU? - posted by Wei Wei via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/29 07:32:47 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] Autotuning for conv2d_nchw and dense_small_batch - posted by Andrew_KR via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/29 09:18:56 UTC, 0 replies.
- [Apache TVM Discuss] [Questions] ReduceNode in TIR - posted by Xqdan via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/30 01:15:24 UTC, 0 replies.