happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
llama.cpp/ggml
History
hung 27104fc7f3 ggml: add GGML_OP_ISTFT with CPU and Vulkan backends 
Adds inverse Short-Time Fourier Transform as a native ggml op, replacing
the hand-rolled iSTFT in tools/tts/tts.cpp. CPU backend uses a direct
inverse DFT (no external dependencies), Vulkan backend uses a parallel
compute shader. Both use Hermitian symmetry for real-valued output.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 		2026-02-13 08:16:39 -05:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include ggml: add GGML_OP_ISTFT with CPU and Vulkan backends 2026-02-13 08:16:39 -05:00
src ggml: add GGML_OP_ISTFT with CPU and Vulkan backends 2026-02-13 08:16:39 -05:00
.gitignore
…
CMakeLists.txt Bump cmake max version (needed for Windows on Snapdragon builds) (#19188) 2026-02-01 14:13:38 -08:00