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

metal : proper assert for mat-mat memory alignment (#6225)

Browse source 
* metal : proper assert for mat-mat memory alignment

ggml-ci

* readme : add notice about the bug fix

* metal : fix the fix

ggml-ci
This commit is contained in:
Georgi Gerganov 2024-03-22 11:35:53 +02:00 • committed by GitHub
parent b2075fd6a5
commit b3e94f26ba
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 41 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

1
README.md
View file

@ -17,6 +17,7 @@ Inference of Meta's [LLaMA](https://arxiv.org/abs/2302.13971) model (and others)
### Hot topics
- Fix major bug in Metal batched inference https://github.com/ggerganov/llama.cpp/pull/6225
- Multi-GPU pipeline parallelizm support https://github.com/ggerganov/llama.cpp/pull/6017
- Looking for contributions to add Deepseek support: https://github.com/ggerganov/llama.cpp/issues/5981
- Quantization blind testing: https://github.com/ggerganov/llama.cpp/discussions/5962