diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-06-05 07:24:31 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-06-05 07:24:31 +0300 |
| commit | 7e79665a31129597634bcef403512aaf4fcdeef9 (patch) | |
| tree | f4ffecdadfba5cf770fc0f88426d77ff0bb5a471 /examples/server/webui/src/components/Sidebar.tsx | |
| parent | f6d5fbdc5780b6dca770c896b8463de3239c7f8b (diff) | |
CUDA implementation for IQ1_S_R4 (#492)
* iq1_s_r4: CUDA dequantize
* iq1_s_r4: CUDA GEMV
* iq1_s_r4: MMQ on CUDA
Requires Turing or better (will fall back to dequantize+cuBLAS on older cards).
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/server/webui/src/components/Sidebar.tsx')
0 files changed, 0 insertions, 0 deletions