llama.cpp/ggml
Eve fbeda9002d
vulkan: matmul dequantization improvements (#12015)
* faster dequant for old quants

* dont use unpack for iq4_nl

* vec2 unpack for q8
2025-02-28 08:20:08 +01:00
..
cmake cmake: Fix ggml backend dependencies and installation (#11818) 2025-02-27 09:42:48 +02:00
include ggml-cpu: Support s390x SIMD Instruction Set (#12019) 2025-02-22 21:39:24 +00:00
src vulkan: matmul dequantization improvements (#12015) 2025-02-28 08:20:08 +01:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt cmake: Fix ggml backend dependencies and installation (#11818) 2025-02-27 09:42:48 +02:00