mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-28 17:07:31 -05:00
* support flash-attention for fp32/fp16/Q4/Q5/Q8 * rm warining * update for JIT
* support flash-attention for fp32/fp16/Q4/Q5/Q8 * rm warining * update for JIT