-
Notifications
You must be signed in to change notification settings - Fork 3.6k
Insights: apache/tvm
Overview
Could not load contribution data
Please try again later
27 Pull requests merged by 9 people
-
[Bugfix][Relax][Pytorch] Bugfix of conv_transpose1d and conv_transpose2d
#17968 merged
May 14, 2025 -
Fix sqrt/rsqrt Compatibility with Integer Data Types
#17953 merged
May 13, 2025 -
Fix basic FLOP estimation for WhileNode
#17961 merged
May 13, 2025 -
[LLVM][Codegen] Enable SVE/VLA for RISCV targets
#17859 merged
May 13, 2025 -
[Fix][Relax] Fix dangling reference in GetTargetFunctions()
#17950 merged
May 13, 2025 -
[Docker][CI] Reintroduce NNEF to CI images
#17955 merged
May 13, 2025 -
[LLVM] Fix JIT unknown reloc issue for case of RISCV
#17958 merged
May 12, 2025 -
[FFI][LLVM] Fix compilation errors with clang20
#17954 merged
May 12, 2025 -
Add registion for the operator asin and acos in llvm
#17945 merged
May 12, 2025 -
[NODE] Fix structural equality for Array<Any> specialization
#17951 merged
May 12, 2025 -
[REFACTOR][FFI][Web] Upgrade Web Runtime to new FFI
#17946 merged
May 11, 2025 -
[TOPI] Add shape validation to prevent negative dimensions in conv operations
#17942 merged
May 11, 2025 -
[FFI] Variant specialize for all ObjectRef
#17943 merged
May 10, 2025 -
[Relax][PyTorch] Add ReLU6 Op Support for Exported Program and FX graph
#17918 merged
May 10, 2025 -
[Relax][PyTorch] Add torch.outer Op Support for Exported Program and FX graph
#17930 merged
May 10, 2025 -
[Relax][PyTorch] Add UpSample Bicubic Op Support for Exported Program and FX graph
#17932 merged
May 10, 2025 -
[Relax][PyTorch] Add AvgPool 1D and 3D Op Support for Exported Program and FX graph
#17921 merged
May 10, 2025 -
[REFACTOR] Phase out legacy rust ffi
#17939 merged
May 10, 2025 -
[REFACTOR] Phase out legacy go ffi
#17940 merged
May 9, 2025 -
[REFACTOR][FFI][RPC] Migrate RPC to use the latest FFI ABI
#17931 merged
May 9, 2025 -
[Relax][PyTorch] Add Adaptive AvgPool 1D and 3D Op Support for Exported Program and FX graph
#17922 merged
May 9, 2025 -
[REFACTOR][FFI] Cleanup container redirections
#17929 merged
May 8, 2025 -
[Relax][PyTorch] CrossEntropyLoss
#17863 merged
May 8, 2025 -
[Relax][PyTorch] Add MaxPool 1D and 3D Op Support for Exported Program and FX graph
#17919 merged
May 8, 2025 -
[Relax][PyTorch] Add tests for all the dtypes supported in the PyTorch frontend
#17926 merged
May 8, 2025 -
[FFI][FEAT] AutoDLPack for taking external tensor objects
#17927 merged
May 8, 2025 -
[REFACTOR][FFI] Cleanup PackedFunc related redirection
#17923 merged
May 7, 2025
6 Pull requests opened by 5 people
-
[KVCache] Per Layer Sliding Window
#17928 opened
May 7, 2025 -
added op support for frac op
#17962 opened
May 12, 2025 -
Add registion for the operator asinh, acosh, atanh in llvm
#17969 opened
May 13, 2025 -
[Doc][Relax][MetaSchedule] Fix errors in the e2e_opt_model.py tutorial
#17971 opened
May 13, 2025 -
Fix g.costs
#17972 opened
May 14, 2025 -
Fix FLOP estimation for EvaluateNode by implementing VisitStmt_ handler
#17974 opened
May 14, 2025
8 Issues closed by 4 people
-
[Bug] CodeGenVM cannot handle this intrinsic now: Op(relax.nn.conv2d_transpose)
#17890 closed
May 14, 2025 -
[Bug] Cannot find intrinsic declaration, possible type mismatch: llvm.sqrt
#17952 closed
May 13, 2025 -
[Bug][MetaSchedule] TVMError: Do not have a default for tir.While
#17960 closed
May 13, 2025 -
[Bug] InternalError: Do not have a default for tir.While
#17948 closed
May 12, 2025 -
[Bug] TVMError: unknown intrinsic Op(tir.acos)
#17944 closed
May 12, 2025 -
[Bug] tvm._ffi.base.TVMError: std: :bad_alloc
#17941 closed
May 11, 2025 -
CodeGenOpenCL: expect calling_conv equals CallingConv::kDeviceKernelLaunch during autotune
#17577 closed
May 8, 2025 -
[Tracking Issue] How to avoid TVM increased tensor dimension?
#17417 closed
May 8, 2025
16 Issues opened by 4 people
-
[Bug] TVMError: Do not have a default for tir.Evaluate
#17973 opened
May 14, 2025 -
[Bug][TOPI] tvm.error.InternalError: unknown intrinsic Op(tir.asinh)
#17967 opened
May 13, 2025 -
[Bug] inconsistent results for the CPU and CUDA targets.
#17965 opened
May 13, 2025 -
[Bug] [CUDA] "hsinh" is undefined when the target is CUDA
#17963 opened
May 13, 2025 -
[Bug] Unsupported Function Type 'frac.default' in ExportedProgram and fx_graph Translator
#17959 opened
May 12, 2025 -
[Bug] [TOPI]te_create_prime cannot generate valid tir for the topk with ret_type='both'
#17956 opened
May 12, 2025 -
[Bug] tensordot produce inconsistency inference results when execuing twice under the same inputs
#17949 opened
May 11, 2025 -
[Bug] Meta schedule produce inconsistant inference results
#17947 opened
May 11, 2025 -
[Bug] InternalError: Check failed: pb->value != 0 (0 vs. 0) : Divide by zero
#17938 opened
May 9, 2025 -
[Bug] InternalError: Check failed: (ret_ex.dtype() == var.dtype()) is false
#17937 opened
May 9, 2025 -
[Bug] InternalError: Check failed: (eval_vec_) is false
#17936 opened
May 9, 2025 -
[Bug] [MetaSchedule] parallel_for_dynamic error with ScheduleError: (not rendered)
#17934 opened
May 9, 2025 -
[Bug] [MetaSchedule] sch.mod returns None after meta scheduling
#17933 opened
May 9, 2025
9 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] How to migrate from te.create_schedule and auto_scheduler to TVM v0.20’
#17914 commented on
May 9, 2025 • 0 new comments -
[Bug] BANAN Pi, RISC-V LLVM Error with TVM 0.20, LLVM 20.1.4
#17916 commented on
May 12, 2025 • 0 new comments -
[Bug] Build fails with LLVM20
#17823 commented on
May 12, 2025 • 0 new comments -
[Bug] Did you forget to bind?
#17899 commented on
May 13, 2025 • 0 new comments -
[Frontend] Add NNEF frontend
#17053 commented on
May 9, 2025 • 0 new comments -
[Fix] Enhance floormod simplification rules for better expression matching
#17765 commented on
May 11, 2025 • 0 new comments -
fix test_attention
#17883 commented on
May 8, 2025 • 0 new comments -
[Relax][Pytorch] Support Instance Norm Operator
#17885 commented on
May 12, 2025 • 0 new comments -
[Relax][PyTorch] Re-enable test_subgraph_capture in dynamo test
#17925 commented on
May 12, 2025 • 0 new comments