diff options
| author | Georgi Gerganov <ggerganov@gmail.com> | 2023-09-20 20:48:22 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-09-20 20:48:22 +0300 |
| commit | 7eb41179edc56083ef4eb2df7967ac9ff38b34fb (patch) | |
| tree | 2e39af4a7ff3bba90201ccc448177550b04b875b | |
| parent | a5661d7e71d15b8dfc81bc0510ba912ebe85dfa3 (diff) | |
readme : update hot topics
| -rw-r--r-- | README.md | 2 |
1 files changed, 2 insertions, 0 deletions
@@ -11,6 +11,8 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++ ### Hot topics +- Parallel decoding + continuous batching support incoming: [#3228](https://github.com/ggerganov/llama.cpp/pull/3228) \ + **Devs should become familiar with the new API** - Local Falcon 180B inference on Mac Studio https://github.com/ggerganov/llama.cpp/assets/1991296/98abd4e8-7077-464c-ae89-aebabca7757e |