ik_llama_opt/ggml
Kawrakow b4be4b17a0
Another minor indexer optimization on the CPU (#2231)
* Convert and repacl f16 K to 4-row-interleaved f32 on AVX2

* Cleanup
2026-08-05 08:15:41 +03:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include DS4: faster long-context TG (#2201) 2026-07-30 13:13:42 +03:00
src Another minor indexer optimization on the CPU (#2231) 2026-08-05 08:15:41 +03:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt Chunked experts (CPU) (#2202) 2026-07-30 13:16:02 +03:00