0cc4m

Results 8 issues of 0cc4m

This change removes the newNotification flag and the clear flag function and replaces it with whether notifications are available (have not been swiped). Thus, the indicator is shown even when...

I often found myself trying to swipe away a new notification, but in the preview this wasn't possible. This small change allows to swipe away notifications from the preview. I'm...

I have been using the deprecated rocm-smi for a while now to monitor the status of my GPUs. I have a FirePro S10000 (Tahiti), which works with amdgpu, but does...

Add CLBlast support as an alternative to CuBLAS to speed up context processing. The advantage of CLBlast over CuBLAS is that it is vendor-agnostic, it runs on basically any GPU...

I had or still have an issue with q5_0 that I can't figure out. On Nvidia trying to transfer the quantized weights to the device leads to a CL_OUT_OF_RESOURCES error....

[output_1.6.1.txt](https://github.com/CNugteren/CLBlast/files/14351215/output_1.6.1.txt) [output_1.6.2.txt](https://github.com/CNugteren/CLBlast/files/14351216/output_1.6.2.txt) In 1.6.1 SGEMM gives the correct results on Intel ARC (tested on an A770 on Arch Linux), but with 1.6.2 the results are wrong. Let me know if...

correctness

I implemented the Operators necessary for stable-diffusion.cpp to run using Vulkan. The corresponding PR is https://github.com/leejet/stable-diffusion.cpp/pull/291 Image generation works now, but I want add some minor stuff for LORA/TAESD (https://github.com/leejet/stable-diffusion.cpp/pull/291#issuecomment-2256572656),...

I have implemented a number of Vulkan optimizations and fixes: - Implement REPEAT operator shader to fix low performance of Vulkan copy-based implementation - Use GLSL FMA instruction where possible...

performance
Vulkan
bugfix
Review Complexity : Medium
ggml