v3.4.2

Based on ggml-org/llama.cpp b7772 (https://github.com/ggml-org/llama.cpp/releases/tag/b7772)

Also available at: DockerHub

v3.4.1

Based on ggml-org/llama.cpp b7286 (https://github.com/ggml-org/llama.cpp/releases/tag/b7286)

• Automatic Flash Attention selection feature (-fa auto). See ampere.md for more details.

Also available at: DockerHub

v3.4.0

Based on ggml-org/llama.cpp b6735 (https://github.com/ggml-org/llama.cpp/releases/tag/b6735)

• Flash Attention for SWA models fixed
• New Flash Attention algorithm. It is optimized for long contexts (above 1024). See
  "Flash Attention algorithm selection" section for details how to select attention algorithm
  manually.

Also available at: DockerHub

v3.3.1

Also available at: DockerHub

v3.3.0

Also available at: DockerHub

v3.2.1

Also available at: DockerHub

v3.2.0

Also available at: DockerHub

v3.1.2

Also available at: DockerHub

v3.1.0

Also available at: DockerHub

v2.2.1

Update benchmark.py