| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2024-07-27 | Merge mainline llama.cpp (#3) | Kawrakow | |
| * Merging mainline - WIP * Merging mainline - WIP AVX2 and CUDA appear to work. CUDA performance seems slightly (~1-2%) lower as it is so often the case with llama.cpp/ggml after some "improvements" have been made. * Merging mainline - fix Metal * Remove check --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com> | |||
| 2024-06-04 | ggml : remove OpenCL (#7735) | Georgi Gerganov | |
| ggml-ci | |||
| 2024-05-20 | llama : remove MPI backend (#7395) | slaren | |
| 2024-03-26 | cuda : rename build flag to LLAMA_CUDA (#6299) | slaren | |
| 2023-10-02 | cmake : fix transient definitions in find pkg (#3411) | bandoti | |
| 2023-09-14 | cmake : add relocatable Llama package (#2960) | bandoti | |
| * Keep static libs and headers with install * Add logic to generate Config package * Use proper build info * Add llama as import library * Prefix target with package name * Add example project using CMake package * Update README * Update README * Remove trailing whitespace | |||
 |
index : ik_llama.cpp.git | |
| Unnamed repository; edit this file 'description' to name the repository. |
| summaryrefslogtreecommitdiff |