LLAMA.cpp setup

📄️Run

Docker

🗃Benchmark

1 item

🗃Recipes

2 items

📄️ROCm * graphs * GPUs bench

These numbers were collected with an older toolchain (llama.cpp b9180, ROCm 6.3.3 / 7.2.3) and are kept for history. See the current run: ROCm 6.3.3 … 10.0 bench.

📄️ROCm 6.3.3 … 10.1 bench

- ROCm 6.3.3|7.2.4|7.14|10.0|10.1 split tensor|layer GPUs 1|2|4 * ctx 0|16K|32K|64K

📄️mxxm fork vs ggml

- fork: mxxm-t/mx-llama.cpp b10951 (a2780ef), 0.3.0-dev