Update to use llama.cpp/master-aacdbd4#8
Open
alexrozanski wants to merge 355 commits intov2from update-llama-cpp-aacdbd4
+25,702-5,965
Commits
This pull request is big! We're only showing the most recent 250 commits
Commits on May 2, 2023
- authored
- authored
- authored
- authored
- authored
- committed
- committed
- authored
- authored
Commits on May 3, 2023
- authored
- authored
- authored
- authored
- authored
- authored
- committed
- authored
- authored
- committed
Commits on May 4, 2023
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on May 5, 2023
- authored
- authored
- authored
- authored
Commits on May 6, 2023
Commits on May 7, 2023
Commits on May 8, 2023
- authored
- authored
- authored
- authored
- authored
- authored
Commits on May 10, 2023
Commits on May 11, 2023
Commits on May 12, 2023
Commits on May 13, 2023
- authored
- committed
- authored
- authored
- committed
- authored
- committed
ggml : implement backward pass for llama + small training-llama-from-scratch example (ggerganov#1360)
- authored
- committed
- committed
- committed
Commits on May 14, 2023
- committed
- authored
- authored
ggml : alternative fix for race condition bug in non-inplace ggml_compute_forward_diag_mask_f32 (ggerganov#1454)
- authored
- authored
Commits on May 15, 2023
Commits on May 16, 2023
- authored
- authored
- authored
- authored
Commits on May 17, 2023
Commits on May 18, 2023
Commits on May 19, 2023
- committed
- authored
- authored
- committed
- authored
Commits on May 20, 2023
- committed
- committed
- authored
- authored
- committed
- committed
cuda : loading models directly into VRAM, norm calculation on GPU, broadcasting for ggml_mul (ggerganov#1483)
authored- authored
- authored
- authored
- committed
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?v=4&size=32){kind=avatar}
Commits on May 21, 2023
Commits on May 22, 2023
Commits on May 23, 2023
Commits on May 24, 2023
Commits on May 25, 2023
Commits on May 26, 2023
Commits on May 27, 2023
- committed
- authored
- committed
- authored
- authored
- authored
- authored
Commits on May 28, 2023
- authored
- authored
- authored
- authored
- authored
Commits on May 29, 2023
Commits on May 30, 2023
Commits on Jun 4, 2023
Commits on Jun 5, 2023
- committed
- authored
- authored
- authored
- authored
- authored
Commits on Jun 6, 2023
- committed
- committed
- committed
- authored
- committed
- authored
- committed
- committed
Commits on Jun 7, 2023
- authored
- authored
- authored
- authored
Commits on Jun 8, 2023
- authored
- committed
- authored
- authored
- authored
- committed
Commits on Jun 9, 2023
- authored
- committed
- authored
- authored
Commits on Jun 10, 2023
- authored
- authored
llama : support requantizing models instead of only allowing quantization from 16/32bit (ggerganov#1691)
authored- committed
- authored
- authored
- authored
- committed
Commits on Jun 11, 2023
Commits on Jun 12, 2023
- authored
Commits on Jun 13, 2023
- authored
- authored
- authored
Commits on Jun 14, 2023
Commits on Jun 15, 2023
- authored
- authored
- authored
- authored
- authored
- authored
- committed
- authored
Commits on Jun 16, 2023
- authored
- authored
- authored
- authored
- authored
Commits on Jun 17, 2023
- authored
- authored
- authored
- authored
- authored
exposed modules so that they can be invoked by nix run github:ggerganov/llama.cpp#server etc (ggerganov#1863)
authored- authored
- authored
- authored
- committed
- authored
- committed
- committed
Commits on Jun 18, 2023
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Jun 19, 2023
- authored
- authored
- committed
- authored
- committed
- authored
Commits on Jun 20, 2023
- authored
- committed
- committed
- committed
- committed
- committed
- committed
- committed
