ggml/llama.cpp releases: b11046

TL;DR

The ggml/llama.cpp project has released an update that adds support for the `flash_attn_f32_f16_bin` kernel in OpenCL, enhancing computational efficiency for certain operations. This update is significant as it improves performance in processing tasks related to large language models.

Detailed Summary

The ggml/llama.cpp project has released an update that includes support for the `flash_attn_f32_f16_bin` bin kernel in OpenCL, enhancing computational efficiency. This update is part of a broader effort to optimize machine learning models, particularly those involving attention mechanisms. The changes will have implications for developers and users working with these models on platforms supporting OpenCL.

Key Points

• • opencl: add support for bin kernel `flash_attn_f32_f16_bin`
• • opencl: guarded prefill fa