| Age | Commit message (Expand) | Author |
|---|---|---|
| 2024-06-22 | iqk_mul_mat: be independent of llamafile_sgemm (WIP) | Iwan Kawrakow |
| 2024-06-22 | iqk_mul_mat: add ability to disable it | Iwan Kawrakow |
| 2024-06-22 | iqk_mul_mat: be able to handle any f16/f32 combination on AVX2 | Iwan Kawrakow |
| 2024-06-22 | iqk_mul_mat: fp16 for Arm | Iwan Kawrakow |
| 2024-06-22 | iqk_mul_mat: fp16 implementation for AVX2 | Iwan Kawrakow |
| 2024-06-22 | iqk_mul_mat: make it independent of sgemm | Iwan Kawrakow |
| 2024-06-22 | iqk_mul_mat for llama.cpp | Iwan Kawrakow |
| 2024-06-18 | Fix no gcc pragma on Windows (#7751) | jojorne |
| 2024-05-08 | sgemm : AVX Q4_0 and Q8_0 (#6891) | Eve |
| 2024-04-26 | llamafile : use 64-bit integers in sgemm (#6928) | Justine Tunney |
| 2024-04-22 | llamafile : improve sgemm.cpp (#6796) | Justine Tunney |
| 2024-04-16 | ggml : add llamafile sgemm (#6414) | Justine Tunney |
