whisper.cpp

mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-10 00:05:41 +02:00

Files

T

Shouyu c9e9f083c2 ggml-hexagon: optimize activation function (llama/18393)

* refactor: refactor silu

* refactor: optimize swiglu

* refactor: remove unncessary if in swiglu

* refactor: refactor swiglu_oai

* chore: fix formatting issue

2026-01-14 09:11:59 +02:00

htp

ggml-hexagon: optimize activation function (llama/18393)

2026-01-14 09:11:59 +02:00

CMakeLists.txt

ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (llama/17977)

2025-12-31 17:52:09 +02:00

ggml-hexagon.cpp

ggml-hexagon: create generalized functions for cpu side op (llama/17500)

2025-12-31 17:52:09 +02:00

htp-utils.c

ggml-hexagon: Initial Hexagon v68/v69 support (llama/17394)

2025-12-12 17:53:06 +02:00

htp-utils.h

ggml-hexagon: create generalized functions for cpu side op (llama/17500)

2025-12-31 17:52:09 +02:00

op-desc.h

ggml-hexagon: create generalized functions for cpu side op (llama/17500)

2025-12-31 17:52:09 +02:00