All issues

Search results

[CUDA] getHalfFloatValue() on a local HalfFloat[] element: ClassCastException HalfFloatStamp -> AbstractPointerStamp (silently bails to sequential)

Status: Open.

#1097 In beehive-lab/TornadoVM;

· mikepapadim opened on Sep 18, 2026

[cuda][profiler] Dispatch times are structurally 0 and copy-out time is never recorded, failing three non-whitelisted TestProfiler tests

Status: Open.

#1071 In beehive-lab/TornadoVM;

· mikepapadim opened on Sep 4, 2026

[CUDA] Lowering fails with "Node implementing Lowerable not handled: NewInstance" when a ternary precedes an allocation (Math.max works)

bugSomething isn't workingSomething isn't working

compiler

Status: Open.

#1064 In beehive-lab/TornadoVM;

· mikepapadim opened on Sep 2, 2026

[CUDA] CuDnn.sdpaForward launches no kernel: silently returns an all-zero result (shipped BenchmarkSdpa fails on 6.0.0)

bugSomething isn't workingSomething isn't working

CUDA

Status: Open.

#1063 In beehive-lab/TornadoVM;

· mikepapadim opened on Sep 2, 2026

TransformerKernelsTest#testReductionOneBlockWithLayer is non-deterministic: inter-workgroup race in the test kernel

Status: Open.

#1059 In beehive-lab/TornadoVM;

· mikepapadim opened on Aug 29, 2026

TornadoParallelScheduler: incorrect thread offset computation in scheduling for non-zero loop start with non-unit stride

Status: Open.

#1044 In beehive-lab/TornadoVM;

· karan-kamat opened on Aug 25, 2026

[bug] A batched plan with more than one output fails with a null device buffer at LAUNCH

bugSomething isn't workingSomething isn't working

Status: Open.

#1034 In beehive-lab/TornadoVM;

· mikepapadim opened on Aug 6, 2026

[perf] Host-side runtime overhead: where the time actually goes, the fixes, and what is left

Status: Open.

#1028 In beehive-lab/TornadoVM;

· mikepapadim opened on Aug 6, 2026

CUDA graph replay fails with CUresult=700 when a captured graph's buffers are re-pointed, and the failure is silent

Status: Open.

#1006 In beehive-lab/TornadoVM;

· mikepapadim opened on Jul 30, 2026

CUDA backend feature roadmap: KernelContext and ExecutionPlan coverage, gaps and priorities

Status: Open.

#990 In beehive-lab/TornadoVM;

· mikepapadim opened on Jul 26, 2026

Auto-tuning of thread configuration via TornadoExecutionPlan.withAutoTune()

Status: Open.

#979 In beehive-lab/TornadoVM;

· mikepapadim opened on Jul 24, 2026

TornadoVM 6.0.0 Roadmap: legacy backends & JVMCI removals, and NVIDIA broader library support

Status: Open.

Task

#957 In beehive-lab/TornadoVM;

· mikepapadim opened on Jul 20, 2026