discuss-archive  

Messages by Thread

• [Apache TVM Discuss] [Questions] Cannot find tuned schedules for target=cuda -keys=cuda,gpu -arch=sm_86 -max_num_threads=1024 -thread_warp_size=32, Jagdish Kolhe via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Kernel Launching and Dynamic Kernel Selection for LLMs with Relay tqchen via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Kernel Launching and Dynamic Kernel Selection for LLMs with Relay Ryan Tomich via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [USMP][UMA] Pin buffer in "main" to a specific memory pool Ehab Ibrahim via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How to get moving_var and moving_mean in batchnorm layer in Relay Stoner via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How to figure out Target device type of a CallNode yogeesh via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] AnnotateUsedMemory does not support dynamic shapes ccang via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Relay.frontend.form_onnx return empty params Bobo~ via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Problem with linking cutlass in tvm 5862www via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Inquiry About Obtaining PTX Assembly Code from TVM akamiri via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Inquiry About Obtaining PTX Assembly Code from TVM Lei Wang via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Inquiry About Obtaining PTX Assembly Code from TVM Siyuan Feng via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Inquiry About Obtaining PTX Assembly Code from TVM tsu-bin via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Slower Execution Times After 8 bit Quantization? Zack via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Slower Execution Times After 8 bit Quantization? Lei Wang via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Slower Execution Times After 8 bit Quantization? 电线杆 via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Slower Execution Times After 8 bit Quantization? sakura via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [TIR][Schedule] pad_einsum not working with padding only on the batch axis Nicolas via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [PIM][BYOC] How to make generated C modules aware of a global member in Custom Codegen yogeesh via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [Relax][Relay] Question of the roadmap of Relax IR chunit via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [Relax][Relay] Question of the roadmap of Relax IR chunit via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [Question] Partitioning DNN with `graph_split()` of `test_pipeline_executor` libr via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How to extract relay.Constant value? nineis via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Error with Relax while build llama with mlc-llm build.py:Module hip should be either dso exportable or binary serializable cydia via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] In TVM, do we have to manually specify a schedule? Ruihang Lai via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] TVM hexagon can not run ---rpc error wen via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] TVM hexagon can not run ---rpc error wen via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] TVM hexagon can not run ---rpc error wen via Apache TVM Discuss
• [Apache TVM Discuss] [Application] TVM Benchmark for Intel CPU/GPU tumbleweed via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [MetaScheduler] Can't optimize resnet50 with tensorcore Ming-Hsuan-Tu via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [MetaSchedule] [TensorCore]Please help check whether I use cuda-tensorcore to tune the operator Ming-Hsuan-Tu via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Questions about IR Expressions - RelayExpr & RelayExprNode Yang Yuanzhao via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Questions about IR Expressions - RelayExpr & RelayExprNode Yang Yuanzhao via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Questions about IR Expressions - RelayExpr & RelayExprNode Anirudh via Apache TVM Discuss
• [Apache TVM Discuss] [Application] Trouble building examples on RPI4 & MacOS for Cpp tvm_newbie via Apache TVM Discuss
  • [Apache TVM Discuss] [Application] Trouble building examples on RPI4 & MacOS for Cpp WashSwang via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Reshapes when importing tflite model Kjetil Østerås via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] AttributeError: Module has no function '__tvm_main__' anders via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] AttributeError: Module has no function '__tvm_main__' Rikora via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [Unity] [Relax] [ONNX Frontend] How could I register a custom operator of ONNX? Civitasv via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [Question] How TVM run text generation model like gpt2 zqh via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [Relax] How to initialize tvm.relax.testing.nn.Parameter with a real tensor anders via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [Relax] How to initialize tvm.relax.testing.nn.Parameter with a real tensor Crispyberry via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [TVMScript] fail to print predicate info of BufferLoad,BufferStore chunying via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [TVMScript] fail to print predicate info of BufferLoad,BufferStore Siyuan Feng via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] VTA graph packing denis via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Can tvm support orin qnx dishow via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Same TVM Quantize method result in different performances AnuNaki via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [BYOC] PyTorch upsample_bilinear2D not represented correctly in Relay AQSingh via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [BYOC] how to check BYOC result? Li via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [unity] confuse about cuda kernel codegen TaoWei via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [Relay]Why the relay vm has no `system_lib:bool` or `runtime:tvm.runtime.Runtime` options to build yanghaku via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] What is the difference between tvm.tir.const and ir_builder.allocate_const in TVM graph construction using tir? Infi_zc via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] What is the difference between tvm.tir.const and ir_builder.allocate_const in TVM graph construction using tir? tqchen via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] What is the difference between tvm.tir.const and ir_builder.allocate_const in TVM graph construction using tir? Infi_zc via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [Rpc Related] What's the difference between rpc_proxy / rpc_server / rpc_tracker? Johnson9009 via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [Rpc Related] What's the difference between rpc_proxy / rpc_server / rpc_tracker? Anirudh via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [VTA] Deploy a model on VTA and get no execution statistics shlrao via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [VTA] Deploy a model on VTA and get no execution statistics xhmelon🇨🇳🍈 via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Relax AlterOpLayout with AXIS_SEPARATOR abhikran-quic via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] TensorIR: Scheduling the init field of block Michael J. Klaiber via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How do I run my CUDA code in TVM? 夏余鑫 via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How to use microTVM with mimxrt1060_evk YAETHeryk via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [Rust Runtime][WASM] How to compile the model loading+execution to WASM barak3d via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [BYOC] Is there a way to export accelerator specific mesurements MartinF via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [BYOC] Is there a way to export accelerator specific mesurements F Pecc via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [BYOC] Is there a way to export accelerator specific mesurements MartinF via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [BYOC] Is there a way to export accelerator specific mesurements F Pecc via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Why SimplifyInference use CreateFunctionPass to create Pass 578881718 via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Why SimplifyInference use CreateFunctionPass to create Pass Junru Shao via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Why SimplifyInference use CreateFunctionPass to create Pass 578881718 via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Understanding Lower TIR Jiyu Hu via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] The bigger flop, the slower it gets optimized with TVM? JJZOU via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How to set cmake.config to let TVM support spirv? qidongzhao via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How to set cmake.config to let TVM support spirv? masahi via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How to set cmake.config to let TVM support spirv? qidongzhao via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [MetaSchedule] PostOrderApply cannot deal with newly added blocks Jinkun Chen via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [MetaSchedule] PostOrderApply cannot deal with newly added blocks Junru Shao via Apache TVM Discuss
• [Apache TVM Discuss] [Application] Will TVM support JAX? Yuan via Apache TVM Discuss
  • [Apache TVM Discuss] [Application] Will TVM support JAX? masahi via Apache TVM Discuss
• [Apache TVM Discuss] [Application] [SOLVED] C++ inference test app doesn't work correctly Temirlanzzz via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How to deal with prim::DictConstruct popojames via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How to deal with prim::DictConstruct masahi via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How to deal with prim::DictConstruct popojames via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [BYOC] How backwards compatible does the TensorRT partition_for_tensorrt function need to be? Mark Shields via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [BYOC] How backwards compatible does the TensorRT partition_for_tensorrt function need to be? masahi via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [BYOC] How backwards compatible does the TensorRT partition_for_tensorrt function need to be? Cody H. Yu via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [BYOC] How backwards compatible does the TensorRT partition_for_tensorrt function need to be? Mark Shields via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [BYOC] How backwards compatible does the TensorRT partition_for_tensorrt function need to be? jian-s via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [BYOC] How backwards compatible does the TensorRT partition_for_tensorrt function need to be? Mark Shields via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [AutoScheduler] Cannot break Sample Init Population loop Lianmin Zheng via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [AutoScheduler] Cannot break Sample Init Population loop XuZhi via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Auto-scheduling Problem on CUDA Lianmin Zheng via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Auto-scheduling Problem on CUDA Andrewwang0612 via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Ansor - number of tuning trials Lianmin Zheng via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] An error occurs when compiling the H5 model using TVM Changshu Lin via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How to set CPU of Hexagon simulator? Iktsuarpokk via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How to set CPU of Hexagon simulator? Krzysztof Parzyszek via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How to set CPU of Hexagon simulator? Iktsuarpokk via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Double_buffer schedule conflict with tenorize F Pecc via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Question about relay.build 张新硕 via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Adding manual scratchpad management code in custom TIR pass 夏余鑫 via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How do I add custom data load and write back through TIR? 夏余鑫 via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How do I add custom data load and write back through TIR? F Pecc via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How do I add custom data load and write back through TIR? 夏余鑫 via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How do I add custom data load and write back through TIR? F Pecc via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How do I add custom data load and write back through TIR? 夏余鑫 via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Intution on why this int8 algorithm is slower? Wheest via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Intution on why this int8 algorithm is slower? masahi via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Intution on why this int8 algorithm is slower? Wheest via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [Tensorflow] AttributeError: <class 'tvm.relay.expr.Call'> has no attribute name_hint Homagni Saha via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Is it possible to run two inference models concurrently in vta? Luo via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Is it possible to run two inference models concurrently in vta? huajsj via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Could we know detail about the applied optimization level? MartinF via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] TVMError: Check failed: (status == cutlass::Status::kSuccess) is false ycliu via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How params are converted and stored in lib.get_params() Ligeng Zhu via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How params are converted and stored in lib.get_params() Jiawei Liu via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How params are converted and stored in lib.get_params() Ligeng Zhu via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How params are converted and stored in lib.get_params() Ligeng Zhu via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How params are converted and stored in lib.get_params() Jiawei Liu via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How params are converted and stored in lib.get_params() Ligeng Zhu via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Multithreaded inference wwq666 via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How to copy data to a fp16 DLTensor? JinTian via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Tvm.device and tvm.target， What are they effects? zxs185996 via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Tvm.device and tvm.target， What are they effects? Jiawei Liu via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Tvm.device and tvm.target， What are they effects? zxs185996 via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Batchnorm op Fusion in TVM Aakanksha via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Batchnorm op Fusion in TVM masahi via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Batchnorm op Fusion in TVM Aakanksha via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Batchnorm op Fusion in TVM masahi via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Batchnorm op Fusion in TVM Aakanksha via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Batchnorm op Fusion in TVM masahi via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Batchnorm op Fusion in TVM Aakanksha via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Batchnorm op Fusion in TVM masahi via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Batchnorm op Fusion in TVM Aakanksha via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Batchnorm op Fusion in TVM masahi via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Batchnorm op Fusion in TVM Ligeng Zhu via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Arm fp16 instruction support huangzhiyuan via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Cross-compilation for CUDA Yg Zhou via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Custom datatypes in AutoScheduler? Victor van Acht via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Custom datatypes in AutoScheduler? Wuwei Lin via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Custom datatypes in AutoScheduler? Victor van Acht via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Custom datatypes in AutoScheduler? Wuwei Lin via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Custom datatypes in AutoScheduler? Victor van Acht via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Custom datatypes in AutoScheduler? Wuwei Lin via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Can One reduce stage fuse into another reduce stage？ JiaNan Wang via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Can One reduce stage fuse into another reduce stage？ masahi via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Why should we set parameter 'shape_dict' when importing models? Liu Yuchen via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Why should we set parameter 'shape_dict' when importing models? Andrew Zhao Luo via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Hot to interpret the log from autotuing Ming-Hsuan-Tu via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Cannot find config for target=llvm -keys=cpu -link-params=0, workload= JJZOU via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Export module using cross compile failed Sina Shahhosseini via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Export module using cross compile failed fake_robot via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Check failed: (code == RPCCode::kReturn) is false: code=kShutdown p via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] `DFPatternRewriteComposer.AddRewrite` with additional args raises compile error Khj809 via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] `DFPatternRewriteComposer.AddRewrite` with additional args raises compile error Matthew Brookhart via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] `DFPatternRewriteComposer.AddRewrite` with additional args raises compile error Altan Haan via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] `DFPatternRewriteComposer.AddRewrite` with additional args raises compile error Khj809 via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [BUG Report] auto dense large gpu schedule chenugray via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] TVMC on NVIDIA JETSON TX2 Sina Shahhosseini via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Generate multiple kernels for operators with symbolic shapes Michael via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Generate multiple kernels for operators with symbolic shapes leeexyz via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Generate multiple kernels for operators with symbolic shapes Michael via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How does python catch exception from c++ in TVM shengxin via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [Auto-schedule] extract_tasks not extract any task from function write in relay Seriushwa via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Hierarchy in TVM Aleks Knezevic via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Hierarchy in TVM Cody H. Yu via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Hierarchy in TVM Xqdan via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Hierarchy in TVM Ligeng Zhu via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Creating own template for Conv1D on ARM CPUs bvoelker via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Optimising pre-trained models with custom layer implementation Akshay via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Getting tvm-generated cuda codes Law Po Wen via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Getting tvm-generated cuda codes carl-tercero via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Getting tvm-generated cuda codes Law Po Wen via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [ONNX] Failed to compile onnx yolov5s model xingyu zhou via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] RTL generation from DNN models satml via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How to manually execute the temporary models created in autotvm tuning, on C++ runtime frank-ff via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How to find proper llvm flags for certain device? p via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [AOT] Ordering of functions definition is random Gilles Miet via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [AOT] Ordering of functions definition is random Mehrdad Hessar via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] [AOT] Ordering of functions definition is random Gilles Miet via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] The "kernel died" problem when testing darknet siweiliu via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Where does Relay OP & TOPI OP connect? sebastian via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Where does Relay OP & TOPI OP connect? Ligeng Zhu via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Where does Relay OP & TOPI OP connect? sebastian via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [Solved] The different results with the same config Heart1998 via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How to lower relay built modules? Ligeng Zhu via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How to lower relay built modules? Christoph Gerum via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How to lower relay built modules? Ligeng Zhu via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] How to lower relay built modules? Christoph Gerum via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Cannot find config for target=llvm -ke JJZOU via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Skip padding calculations in bitserial convolution Jianshitansuantong233 via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [RTX3090][AutoScheduler]fail to generate programes vincentily via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [relay.op.nn] Pooling and ceil_mode Nenad via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Undefined symbol: VTAMemFree Arina Naumova via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Have anyone deployed rpc tracker to k8s cluster? p via Apache TVM Discuss
  • [Apache TVM Discuss] [Questions] Have anyone deployed rpc tracker to k8s cluster? p via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] How is the Python API on tvm.apache.org generated? Missing entry autotvm.task.extract_from_program MartinF via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] [Frontend][Pytorch] nn.ConvTranspose2d - Support for 'aten::uniform_' Abdul Aziz via Apache TVM Discuss
• [Apache TVM Discuss] [Questions] Steps for integrating a new accelerator to TVM Nicolas via Apache TVM Discuss

• Earlier messages