mfritsche 7fbbd7acc3 Merge rknpu-int8-clamp: saturate int8 activation quantization ...

Brings the latent int8 saturation fix onto the main integration branch so the
serving config and its documentation live together.

2026-07-10 12:17:32 +02:00

..

cmake

ggml : Parallelize quant LUT init (#23595)

2026-05-25 10:15:46 +03:00

include

TP: quantized KV cache support (#23792)

2026-06-01 12:30:10 +02:00

src

Merge rknpu-int8-clamp: saturate int8 activation quantization

2026-07-10 12:17:32 +02:00

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

Merge tag 'refs/tags/b9549' into mtp-b9549

2026-07-09 23:24:17 +02:00