Spaces:

Duplicated from natasa365/whisper.cpp

Xenobd
/

whisper.cpp

Running

App Files Files Community

whisper.cpp / ggml /src

6.35 MB

100 contributors

History: 497 commits

midnight

cmake : fix compile assumptions for power9/etc (#2777)

4683df3 unverified 11 months ago

ggml-amx
ggml : adapt AMX to tensor->grad removal (llama/0) about 1 year ago
ggml-blas
ggml : add support for dynamic loading of backends (llama/10469) about 1 year ago
ggml-cann
llama : add Qwen2VL support + multimodal RoPE (llama/10361) about 1 year ago
ggml-cpu
cmake : fix compile assumptions for power9/etc (#2777) 11 months ago
ggml-cuda
CUDA: fix Volta FlashAttention logic (llama/11615) 11 months ago
ggml-hip
CUDA: use mma PTX instructions for FlashAttention (llama/11583) 11 months ago
ggml-kompute
llama : add Qwen2VL support + multimodal RoPE (llama/10361) about 1 year ago
ggml-metal
metal: Handle null returned from MTLCreateSystemDefaultDevice() (llama/11441) 11 months ago
ggml-musa
CUDA: use mma PTX instructions for FlashAttention (llama/11583) 11 months ago
ggml-opencl
ggml : add opencl backend (skip) (llama/10693) 11 months ago
ggml-rpc
rpc : better caching of the base buffer pointer (llama/11331) 11 months ago
ggml-sycl
SYCL : SOFTMAX F16 mask support and other fixes (llama/11261) 11 months ago
ggml-vulkan
vulkan: implement initial support for IQ2 and IQ3 quantizations (llama/11360) 11 months ago
CMakeLists.txt

11.8 kB

`ci`: use sccache on windows instead of ccache (llama/11545) 11 months ago
ggml-alloc.c

38.5 kB

CUDA: backwards pass for misc. ops, add tests (llama/11257) 11 months ago
ggml-backend-impl.h

12 kB

rpc : early register backend devices (llama/11262) 11 months ago
ggml-backend-reg.cpp

17.2 kB

ggml : allow loading backend with env variable (ggml/1059) 12 months ago
ggml-backend.cpp

77.5 kB

ggml-backend : only offload from host buffers (fix) (llama/11124) 12 months ago
ggml-common.h

133 kB

CUDA: rename macros to avoid conflicts with WinAPI (llama/10736) about 1 year ago
ggml-impl.h

18.3 kB

GGUF: C++ refactor, backend support, misc fixes (llama/11030) 12 months ago
ggml-opt.cpp

31.7 kB

ggml-opt: fix data corruption (ggml/1022) about 1 year ago
ggml-quants.c

214 kB

ggml : refactor online repacking (llama/10446) about 1 year 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

209 kB

CPU/CUDA: fix (GQA) mul mat back, add CUDA support (llama/11380) 11 months ago
gguf.cpp

45 kB

cmake : add sanitizer flags for llama.cpp (llama/11279) 11 months ago