All pull requests

Pull requests

• fix transformers scan issue

  ci: fullcla signedcomponent: build systemcomponent: tests
  #4938·lanluo-nvidia opened Oct 28, 2026Collaborator·2/2·7 tasks·

  ·

• fix nspec scan vulnerbility

  ci: fullcla signedcomponent: api [Python]component: build system
  #4937·lanluo-nvidia opened Oct 28, 2026Collaborator·1/2·7 tasks·

  ·
  

• fix(dynamo): several correctness and speed fixes found compiling large models

  ci: fullcla signedcomponent: api [Python]component: conversioncomponent: converterscomponent: corecomponent: dynamocomponent: loweringcomponent: runtimecomponent: tests
  #4936·shoumikhin opened Oct 27, 2026Contributor·

  ·
  2

• feat: support aten.masked_select by decomposing to boolean indexing

  cla signedcomponent: api [Python]component: corecomponent: dynamocomponent: loweringcomponent: tests
  #4935·Baiiiiiiiiii opened Oct 27, 2026·5 of 7 tasks·

  ·
  1

  3

• feat: add CuTe DSL AOT kernel frontend

  cla signedcomponent: api [Python]component: build systemcomponent: testsdocumentation
  #4933·bowang007 opened Oct 27, 2026Collaborator·7 tasks·

  ·

• test(runtime): build the compile-memory test engines in fp32

  cla signedcomponent: tests
  #4932·narendasan opened Oct 26, 2026Collaborator·

  ·

• Enable TRT API model tests for TensorRT-RTX

  backend: TensorRT-RTXci:trt-apicla signedcomponent: tests
  #4926·tp5uiuc opened Oct 23, 2026Collaborator·6 tasks done·

  ·
  1

  

• fix : skip FP8 MHA accuracy checks on TRT-RTX 1.7 and earlier

  ci: fullcla signedcomponent: tests
  #4925·tp5uiuc opened Oct 23, 2026Collaborator·2 of 7 tasks·

  ·
  1

  

• fix: validate 3D convolutions on Turing with TensorRT-RTX

  backend: TensorRT-RTXcla signedcomponent: api [Python]component: conversioncomponent: converterscomponent: corecomponent: dynamocomponent: testsdocumentation
  #4924·tp5uiuc opened Oct 23, 2026Collaborator·6 tasks done·

  ·

  · v2.16.0
  

• fix: correct TensorRT-RTX converter tests on Turing and A30

  ci: fullcla signedcomponent: tests
  #4923·tp5uiuc opened Oct 23, 2026Collaborator·5 tasks done·

  ·

  · v2.16.0
  2

  

• fix(lowering): remove aten.alias after decompositions, not during them

  ci: fullcla signedcomponent: api [Python]component: corecomponent: dynamocomponent: loweringcomponent: testscomponent: torch_compile
  #4922·shoumikhin opened Oct 23, 2026Contributor·

  ·

  · v2.15.0
  3

• feat: add structured reporting, verification, and benchmarking workflows for agents

  cla signedcomponent: api [Python]component: build systemcomponent: conversioncomponent: corecomponent: dynamocomponent: testsdocumentation
  #4920·zewenli98 opened Oct 22, 2026Collaborator·7 tasks done·

  ·
  

• feat: agentic region kernel generation

  cla signedcomponent: api [Python]component: build systemcomponent: corecomponent: dynamocomponent: testsdocumentation
  #4914·bowang007 opened Oct 22, 2026Collaborator·1 of 7 tasks·

  ·
  8

• [2.15] Bump the ExecuTorch delegate to 0.2.1, and bring the ExecuTorch docs and build fix from #4927

  cla signedcomponent: api [C++]component: api [Python]component: build systemcomponent: testsdocumentation
  #4909·shoumikhin opened Oct 21, 2026Contributor·

  ·

• fix(runtime): create the warm-up inputs before unflattening them under whole-graph CUDA graphs

  cla signedcomponent: api [Python]component: corecomponent: dynamocomponent: runtimecomponent: tests
  #4907·narendasan opened Oct 21, 2026Collaborator·

  ·

• fix(runtime): keep the output structure under whole-graph CUDA graphs

  cla signedcomponent: api [Python]component: corecomponent: dynamocomponent: runtimecomponent: tests
  #4906·narendasan opened Oct 21, 2026Collaborator·

  ·

• fix(runtime): flatten the inputs by the input spec under whole-graph CUDA graphs

  cla signedcomponent: api [Python]component: corecomponent: dynamocomponent: runtimecomponent: tests
  #4905·narendasan opened Oct 21, 2026Collaborator·

  ·

• fix(runtime): record inputs updated in place as the caller's tensors under whole-graph CUDA graphs

  cla signedcomponent: api [Python]component: corecomponent: dynamocomponent: runtimecomponent: tests
  #4904·narendasan opened Oct 21, 2026Collaborator·

  ·

• fix(conversion): treat a 0 in reshape dims as an empty dimension

  cla signedcomponent: api [Python]component: conversioncomponent: converterscomponent: corecomponent: dynamocomponent: tests
  #4901·narendasan opened Oct 21, 2026Collaborator·

  ·

• fix(conversion): clamp a negative slice start on a dynamic axis

  cla signedcomponent: api [Python]component: conversioncomponent: converterscomponent: corecomponent: dynamocomponent: tests
  #4900·narendasan opened Oct 21, 2026Collaborator·

  ·

• fix(lowering): decompose unfold with a gather instead of as_strided

  cla signedcomponent: api [Python]component: corecomponent: dynamocomponent: loweringcomponent: tests
  #4899·narendasan opened Oct 21, 2026Collaborator·

  ·

• fix(conversion): keep multi-token KV writes converting across engines and off half precision

  cla signedcomponent: api [Python]component: conversioncomponent: corecomponent: dynamocomponent: tests
  #4897·narendasan opened Oct 21, 2026Collaborator·

  ·

• fix(lowering): keep dynamic dims through complex lowering

  cla signedcomponent: api [Python]component: corecomponent: dynamocomponent: loweringcomponent: tests
  #4896·narendasan opened Oct 21, 2026Collaborator·

  ·

• fix(conversion): map as_strided reads through the input's PyTorch memory layout

  cla signedcomponent: api [Python]component: conversioncomponent: converterscomponent: corecomponent: dynamocomponent: tests
  #4895·narendasan opened Oct 21, 2026Collaborator·

  ·

• fix(lowering): keep the write-back of an in-place update to a graph input

  cla signedcomponent: api [Python]component: corecomponent: dynamocomponent: loweringcomponent: tests
  #4894·narendasan opened Oct 21, 2026Collaborator·

  ·