FelixCLC
FelixCLC
Much as the title. Essentially, Cfd OF seems to only use the multi threaded parameter in the CFD mesh workbench when calling GMSH/snappyhexmesh or CFmesh, but does not use it...
Partially a feature request- ability to decode the frame to an ffmpeg cuda frame so that it can be used in conjunction with cuda HW filters directly, instead of going...
For cases where 10 bit signals may be sent to the decoder, the encoder on the nano cannot output 10 bit content. it can however accept a 10 bit source,...
I'm currently implementing the FP16 kernels as a follow up to #3754 and #2767 I want to be 100% clear on OpenBLAS nomenclature prior to submitting my PR. ### Baseline...
This PR provides for the basic infrastructure needed for detecting the presence of hardware for supporting any and all available FP16 capabilities available on x86_64 hardware. FP16 differs from BF16...
**Describe the motivation for the feature request** SYCL on x86 seems to be well catered for by various projects such as DPC++, ComputeCPP as well as hipSYCL amongst others. Support...
**Describe the motivation for the feature request** With Linux on M1/M2 now progressing to the point of having good support via the ASAHI Linux project [Asahi blog-M2 and M1 ultra...
Following up on #1617 https://github.com/RadeonOpenCompute/ROCm/issues/1595 , https://github.com/RadeonOpenCompute/ROCm/issues/1592 https://github.com/RadeonOpenCompute/ROCm/issues/1547 https://github.com/RadeonOpenCompute/ROCm/issues/1544 https://github.com/RadeonOpenCompute/ROCm/issues/1539 We still haven't received an official update other than "soon" for support of: W5700 (Navi 10) W5500 (Navi 14) Radeon...
I'd like to request that https://github.com/apple/ml-stable-diffusion#-performance-benchmark be further fleshed out to include: GPU+CPU+NPU results on the relevant models, as well as CPU only data paths. Ideally results results for higher...