Not AI
I like big .vimrc and I cannot lie
- Sofia, Bulgaria
-
04:43
(UTC +03:00) - https://ggerganov.com
- @ggerganov
- user/ggerganov
Sponsors
Block or Report
Block or report ggerganov
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
1,773 contributions in the last year
Less
More
Contribution activity
June 2023
Created 17 commits in 3 repositories
Opened 2 pull requests in 2 repositories
ggerganov/llama.cpp
1
merged
ggerganov/ggml
1
open
Reviewed 9 pull requests in 1 repository
ggerganov/llama.cpp
9 pull requests
- Multi GPU support, CUDA refactor, CUDA scratch buffer
- Add checks for buffer size with Metal
- docs(performance): Add performance troubleshoot + example benchmark documentation
- fix small typo in README.md
- Share buffers between CPU and GPU
- ggml: Fix internal overflow in ggml_time_us on Windows
- k-quants
- Cuda refactor, multi GPU support
- llama : Metal inference








