mirror of
https://github.com/ggerganov/llama.cpp
synced 2026-04-01 04:45:51 +02:00
* llama : add option to override tensor buffers * ggml : fix possible underflow in ggml_nbytes |
||
|---|---|---|
| .. | ||
| llama-cpp.h | ||
| llama.h | ||
* llama : add option to override tensor buffers * ggml : fix possible underflow in ggml_nbytes |
||
|---|---|---|
| .. | ||
| llama-cpp.h | ||
| llama.h | ||