vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into quick-fixup

Browse source
This commit is contained in:
Galunid 2024-05-31 10:17:18 +02:00
commit 828c176561
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
README.md
View file

@ -22,7 +22,8 @@ Inference of Meta's [LLaMA](https://arxiv.org/abs/2302.13971) model (and others)
### Hot topics ### Hot topics
- **Initial Flash-Attention support:** https://github.com/ggerganov/llama.cpp/pull/5021 - **`convert.py` has been deprecated and moved to `examples/convert-legacy-llama.py`, please use `convert-hf-to-gguf.py`** https://github.com/ggerganov/llama.cpp/pull/7430
- Initial Flash-Attention support: https://github.com/ggerganov/llama.cpp/pull/5021
- BPE pre-tokenization support has been added: https://github.com/ggerganov/llama.cpp/pull/6920 - BPE pre-tokenization support has been added: https://github.com/ggerganov/llama.cpp/pull/6920
- MoE memory layout has been updated - reconvert models for `mmap` support and regenerate `imatrix` https://github.com/ggerganov/llama.cpp/pull/6387 - MoE memory layout has been updated - reconvert models for `mmap` support and regenerate `imatrix` https://github.com/ggerganov/llama.cpp/pull/6387
- Model sharding instructions using `gguf-split` https://github.com/ggerganov/llama.cpp/discussions/6404 - Model sharding instructions using `gguf-split` https://github.com/ggerganov/llama.cpp/discussions/6404