ik_llama_opt/ggml
Kawrakow e962ce8c70 CUDA: faster IQ2_K, IQ2_KS, IQ2_K_R4 (#716)
* Use bperm trick for iq2_ks gemm -> 7% gain

* Use bperm trick for iq2_k gemm -> ~5% gain

* Use bperm trick for iq2_k_r4 gemm -> ~3% gain

* Use bperm trick for iq2_ks gemv -> ~7% gain

* Use bperm trick for iq2_k gemv -> ~3% gain

* Use bperm trick for iq2_k_r4 gemv -> ~7% gain

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-08-22 07:25:35 +03:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include AVX512+AVXVNNI GEMM implementation for quants using Q8_K for activations (#710) 2025-08-22 06:27:07 +03:00
src CUDA: faster IQ2_K, IQ2_KS, IQ2_K_R4 (#716) 2025-08-22 07:25:35 +03:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt Enable CUDA graphs for MoE models + GPT-OSS support (#689) 2025-08-15 09:18:07 +03:00