| Age | Commit message (Expand) | Author |
|---|---|---|
| 2023-07-15 | llama : add custom RoPE (#2054) | Xiao-Yong Jin |
| 2023-07-14 | Metal: faster Q4_0 and Q4_1 matrix x vector kernels (#2212) | Kawrakow |
| 2023-07-12 | metal : new q4_0 matrix-vector kernel (#2188) | Shouzheng Liu |
| 2023-06-26 | k-quants : support for super-block size of 64 (#2001) | Kawrakow |
| 2023-06-17 | metal : add norm, cpy f16->f16, alibi kernels (#1823) | Aaron Miller |
| 2023-06-12 | Metal implementation for all k_quants (#1807) | Kawrakow |
| 2023-06-10 | metal : add Q4_1 implementation (#1785) | Kawrakow |
| 2023-06-09 | metal : fix build "tanhf" -> "tanh" | Georgi Gerganov |
| 2023-06-09 | metal : add GELU implementation (#1770) | AT |
| 2023-06-09 | metal : faster q4_0 (#1775) | Kawrakow |
| 2023-06-08 | metal : add Q2_K implementation (#1762) | Kawrakow |
| 2023-06-08 | metal : Q6_K implementation (#1752) | Kawrakow |
| 2023-06-08 | metal : add Q4_K implementation (#1733) | Kawrakow |
| 2023-06-06 | metal : add f16 support | Georgi Gerganov |
| 2023-06-04 | llama : Metal inference (#1642) | Georgi Gerganov |
 |
index : llama.cpp.git | |
| llama.cpp | user |
| aboutsummaryrefslogtreecommitdiff |
path: root/ggml-metal.metal