whisper.cpp/ggml
Titaniumtown 2d05b6ec1e sycl: fuse the gated-delta-net state writeback cpy (llama/26643)
Port of https://github.com/ggml-org/llama.cpp/pull/23940.

Arc Pro B70, Qwen 3.6 27B Q4_K - Medium (48 of its 64 blocks run
gated_delta_net), -ngl 99 -fa 1 -ctk f16 -ctv f16 -b 2048 -ub 2048,
interleaved A/B passes of r=3:

  tg128           23.91 / 23.90 / 23.90 -> 24.19 / 24.17 / 24.20   +1.2%
  tg128 (rebuild) 23.81 / 23.81         -> 24.09 / 24.10           +1.2%
  pp2048        1050.8  / 1053.9        -> 1053.8 / 1054.5         flat
  2 seqs, tg128    32.73 / 32.75        ->  33.11 / 33.10          +1.1%
2026-08-14 22:16:06 +03:00
..
cmake cmake : add config version support (ggml/1582) 2026-08-14 22:16:06 +03:00
include llama: add default load-mode auto, which avoids mmap on iGPUs (llama/26081) 2026-08-14 22:16:06 +03:00
src sycl: fuse the gated-delta-net state writeback cpy (llama/26643) 2026-08-14 22:16:06 +03:00
.gitignore whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
CMakeLists.txt cmake : add config version support (ggml/1582) 2026-08-14 22:16:06 +03:00