All pull requests

Pull requests

• [Fix][Relax] Scope BasePyModule's Python function registry entries to the module

  #20417·akaashrp opened Sep 22, 2026·

  ·
  2

• [Fix][Relax][ONNX] Support Hardmax over a symbolic axis extent

  #20416·LiRunGuo opened Sep 22, 2026·

  ·

• [Fix][Relax][ONNX] Fix Upsample and Resize-10 import

  #20415·LiRunGuo opened Sep 22, 2026·

  ·

• [Fix][Sym] Use a typed zero for the sign test in interval Mul/Div

  #20414·LiRunGuo opened Sep 22, 2026·

  ·

• [Fix][Relax][VM] Stop BasePyModule from wiping the call_py_func registry

  #20413·LiRunGuo opened Sep 22, 2026·

  ·

• [TIRx] Reject boolean div and mod

  #20412·Nanmur opened Sep 22, 2026·

  ·
  1

• [Fix][Relax][ONNX] Import Resize with empty scales tensor and symbolic sizes

  #20406·LiRunGuo opened Sep 22, 2026·

  ·
  2

• [Fix][Relax][Torch] Respect zero-dimensional tensor dtype promotion

  #20405·jack-k737 opened Sep 22, 2026·

  ·

• [Fix][Relax][ONNX] Support symbolic dims in SAME auto_pad pooling

  #20404·LiRunGuo opened Sep 21, 2026·

  ·
  1

• [FIX][Vulkan] Avoid device API destruction during Windows DLL shutdown

  #20397·sepcnt opened Sep 21, 2026·

  ·
  1

• [Metal] Add TVM_METAL_STORAGE_MODE opt-in for correctness at scale (#20157)

  #20391·zacharywhitley opened Sep 19, 2026·

  ·

• [Relax] Skip 1-D inputs in CombineParallelMatmul

  #20389·Nanmur opened Sep 19, 2026·

  ·
  1

• [Fix][CUDA] Preserve NaNs in floating-point min and max

  #20387·LngelKyo opened Sep 18, 2026·

  ·

• [Fix][Relax][Frontend][Torch] Compare shapes without == on symbolic dims in the reshape shortcut

  #20377·hiyufan opened Sep 17, 2026·

  ·
  1

• [Fix][Relax][Frontend][Torch] Make any and prod follow torch: missing overloads and result dtypes

  #20376·hiyufan opened Sep 17, 2026·

  ·
  1

• [Relax][Frontend][Torch] Add amax, amin and min.dim converters

  #20375·hiyufan opened Sep 17, 2026·

  ·

• [Fix][Relax][Frontend][Torch] Accumulate integer cumsum and cumprod in int64

  #20374·hiyufan opened Sep 17, 2026·

  ·

• [Fix][Relax][Frontend][Torch] Follow torch's dtype rules for the division family

  #20373·hiyufan opened Sep 17, 2026·

  ·

• [Fix][Relax][Frontend][Torch] Promote the tensor, not the scalar, in binary ops with a Python scalar

  #20372·hiyufan opened Sep 17, 2026·

  ·

• [FIX][Relax] Validate DeviceMesh cardinality without overflow

  #20346·ruiling-smartbear opened Sep 15, 2026·

  ·
  1

• [FIX][Relax] Guard unknown tensor shapes in VMShapeLower

  #20345·ruiling-smartbear opened Sep 15, 2026·

  ·
  1

• [FIX][TIR] Conservatively analyze unsigned branch conditions

  #20344·sepcnt opened Sep 15, 2026·

  ·
  2

  6

• [FIX][TIR] Fix fixed-point multiply legalization

  #20341·sepcnt opened Sep 15, 2026·

  ·
  4

• [Arith] Add constraint visitor snapshots

  #20334·tlopex opened Sep 14, 2026·

  ·

• [FIX][Relax] Preserve symbolic shape dependencies in FuseOps

  #20333·Junius-Wynn opened Sep 13, 2026·

  ·
  1