Spaces:

Duplicated from natasa365/whisper.cpp

Xenobd
/

whisper.cpp

Running

App Files Files Community

whisper.cpp / ggml /src

8.06 MB

100 contributors

History: 965 commits

lhez

opencl : add GEGLU, REGLU, SWIGLU (llama/14456)

d70ff9f 6 months ago

ggml-amx
ggml : adapt AMX to tensor->grad removal (llama/0) about 1 year ago
ggml-blas
cmake : Fix broken CMake error messages (ggml/1252) 7 months ago
ggml-cann
fix async_mode bug (llama/14432) 6 months ago
ggml-cpu
Add Conv2d for CPU (llama/14388) 6 months ago
ggml-cuda
ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158) 6 months ago
ggml-hip
HIP: disable rocwmma on gfx12 by default until rocm 7.0 (llama/14202) 6 months ago
ggml-kompute
llama : add Qwen2VL support + multimodal RoPE (llama/10361) about 1 year ago
ggml-metal
metal : disable fast-math for some cpy kernels (llama/14460) 6 months ago
ggml-musa
musa: enable fp16 mma (all) and cublas on qy2 (llama/13842) 6 months ago
ggml-opencl
opencl : add GEGLU, REGLU, SWIGLU (llama/14456) 6 months ago
ggml-rpc
rpc : nicer error messages for RPC server crash (llama/14076) 6 months ago
ggml-sycl
ggml-cpu: sycl: Re-enable exp f16 (llama/14462) 6 months ago
ggml-vulkan
ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158) 6 months ago
CMakeLists.txt

15 kB

Implement GGML_CPU_ALL_VARIANTS for PowerPC (llama/14286) 6 months ago
ggml-alloc.c

38.5 kB

ggml: Don't assert fail when tensor data changes (llama/13222) 8 months ago
ggml-backend-impl.h

12 kB

ggml : upgrade init_tensor API to return a ggml_status (llama/11854) 10 months ago
ggml-backend-reg.cpp

17.5 kB

build : suppress gcc15 compile warnings (llama/14261) 6 months ago
ggml-backend.cpp

79.1 kB

vulkan: Add fusion support for RMS_NORM+MUL (llama/14366) 6 months ago
ggml-common.h

133 kB

ggml-cpu : split arch-specific implementations (llama/13892) 7 months ago
ggml-impl.h

17.7 kB

vulkan: Add fusion support for RMS_NORM+MUL (llama/14366) 6 months ago
ggml-opt.cpp

39.8 kB

mnist: fix segmentation fault (ggml/1227) 7 months ago
ggml-quants.c

215 kB

ggml-quants : rename best_mad to best_error (ggml/1283) 6 months ago
ggml-quants.h

8.34 kB

ggml : build backends as libraries (llama/10256) about 1 year ago
ggml-threading.cpp

250 Bytes

ggml : build backends as libraries (llama/10256) about 1 year ago
ggml-threading.h

198 Bytes

remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797) about 1 year ago
ggml.c

218 kB

Add Conv2d for CPU (llama/14388) 6 months ago
ggml.cpp

738 Bytes

ggml : Print backtrace on uncaught C++ exceptions (ggml/1232) 7 months ago
gguf.cpp

46.1 kB

ggml : do not output unprintable characters on GGUF load failure (llama/14381) 6 months ago