Utkarsh
Utkarsh
Yeah, I'll take a look.
I will be adding tests shortly, but with the given MWE (which is in ode_cache_tests.jl), why resizing of `integrator.u` does not happen in the cases of QNDF and Extrapolation Methods?
Okay yeah, so in tests of `ode_cache_tests.jl` (prob is the same as defined above): ``` julia> sol = solve(prob,KenCarp4(),callback=callback) julia> sol = solve(prob,KenCarp4(),callback=callback) retcode: Success Interpolation: 3rd order Hermite t:...
Where should be the tests added for this?
Sounds good to me. I will start writing some documentation for it. I can help setting up docs page for it, something aligned with SciMLDocs.
Try `EnsembleGPUKernel`. It probably works with MTK-generated functions.
Fixed via #241.
Hi, The data can be found here: https://github.com/utkarsh530/GPUODEBenchmarks/tree/main/paper_artifacts/data. You can use either `Tesla V100` or `RTX 5000` data points. The first column indicates the no. of trajectories, with the second...
I think it’s a bit tricky to add this feature, because of different sized arrays for each solve, which might not be good with `CuMatrix` which has all `ts,us` stored...
The above example works on `[email protected]` and `[email protected]`