ik_llama_opt/ggml
Marvin e2728c8547 qwen4exp: PP/TG opts for Ampere+Zen3 (merged experts, fused PLE taps, Zen3 tiling) 2026-09-05 20:14:29 -03:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include Quantization fudge factors (#2361) 2026-08-27 17:35:04 +02:00
src qwen4exp: PP/TG opts for Ampere+Zen3 (merged experts, fused PLE taps, Zen3 tiling) 2026-09-05 20:14:29 -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