readme : update hot topics

This commit is contained in:
Georgi Gerganov 2023-10-18 21:44:43 +03:00 committed by GitHub
parent 4e82b2ea3f
commit 004797f6ac
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -10,13 +10,9 @@
Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++
### Hot topics ### Hot topics
- ‼️ BPE tokenizer update: existing Falcon and Starcoder `.gguf` models will need to be reconverted: [#3252](https://github.com/ggerganov/llama.cpp/pull/3252)
- ‼️ Breaking change: `rope_freq_base` and `rope_freq_scale` must be set to zero to use the model default values: [#3401](https://github.com/ggerganov/llama.cpp/pull/3401)
- Parallel decoding + continuous batching support added: [#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 - LLaVA support: https://github.com/ggerganov/llama.cpp/pull/3436
- ‼️ BPE tokenizer update: existing Falcon and Starcoder `.gguf` models will need to be reconverted: [#3252](https://github.com/ggerganov/llama.cpp/pull/3252)
---- ----