ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations#17977
Merged
max-krasnyansky merged 4 commits intoggml-org:masterfrom Dec 19, 2025
Commits
Commits on Dec 12, 2025
- committed
ngdxzy
Commits on Dec 14, 2025
Commits on Dec 18, 2025
- committedngdxzy
- committedngdxzy