8 Pull requests merged by 5 people

• [TOPI] Support integer type input for log10

  #18015 merged May 29, 2025

• [REFACTOR][PYTHON] Phase out tvm._ffi and Limited API support

  #18020 merged May 28, 2025

• Add op support for slice_scatter

  #18019 merged May 28, 2025

• Fix FLOP estimation for EvaluateNode by implementing VisitStmt_ handler

  #17974 merged May 28, 2025

• [Relax][ONNX] Replace deprecated mapping.TENSOR_TYPE_TO_NP_TYPE usage

  #18016 merged May 27, 2025

• Fix RuntimeError: parallel_for_dynamic

  #18013 merged May 27, 2025

• Fix division truncation in window size calculation for small dtypes in average_pool

  #18014 merged May 26, 2025

• [REFACTOR][FFI] Phase out legacy C API

  #18010 merged May 24, 2025

3 Pull requests opened by 3 people

• Fix: [RELAX][FRONTEND][Resolved from_onnx import issue #18008]

  #18009 opened May 23, 2025

• [TOPI][NN][Layer_Norm] Fix layer_norm error with reduce-only axes

  #18012 opened May 25, 2025

• [REFACTOR][FFI] Cleanup PackedFunc redirections

  #18022 opened May 29, 2025

3 Issues closed by 3 people

• [Bug] Cannot find intrinsic declaration, possible type mismatch: llvm.log10

  #17996 closed May 29, 2025

• [Bug] TVMError: Do not have a default for tir.Evaluate

  #17973 closed May 28, 2025

• [Bug] InternalError: Check failed: pb->value != 0 (0 vs. 0) : Divide by zero

  #17938 closed May 26, 2025

3 Issues opened by 2 people

• [Bug][meta_schedule] Tutorial `e2e_opt_model.py` fails

  #18018 opened May 26, 2025

• [CI Problem] lint check has a bug

  #18017 opened May 26, 2025

• [Bug] tvm.relax.frontend.onnx.from_onnx(...) Issue

  #18008 opened May 23, 2025

7 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• [Bug] MetaSchedule lead to a significant difference in the reference results for the log_softmax operator

  #17935 commented on May 23, 2025 • 0 new comments

• [Bug] inconsistent results for the CPU and CUDA targets.

  #17965 commented on May 23, 2025 • 0 new comments

• [Bug] Inconcistency after meta schedule for the conv2d_hwcn operator

  #17997 commented on May 24, 2025 • 0 new comments

• [Bug] Did you forget to bind?

  #17899 commented on May 24, 2025 • 0 new comments

• [Bug] The output of the TVM CPU backend is not identical with those of onnxruntime and TVM CUDA backend

  #18003 commented on May 26, 2025 • 0 new comments

• [Codegen] Resolve issue #17965 where the same model produces different outputs on the LLVM (CPU) and CUDA (GPU) backends

  #17985 commented on May 24, 2025 • 0 new comments

• [TOPI] Fix index handling in expand_like operator for axis expansion

  #18006 commented on May 29, 2025 • 0 new comments