Spaces:

Duplicated from natasa365/whisper.cpp

Xenobd
/

whisper.cpp

Running

App Files Files Community

whisper.cpp / ggml /src

6.99 MB

100 contributors

History: 648 commits

ggerganov's picture

metal : improve FA + improve MoE (llama/12612)

04a3389 9 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
MUL_MAT optimization (llama/12382) 9 months ago
ggml-cpu
metal : improve FA + improve MoE (llama/12612) 9 months ago
ggml-cuda
metal : improve FA + improve MoE (llama/12612) 9 months ago
ggml-hip
HIP: implement FlashAttention via rocWMMA for CDNA and RDNA3+ (llama/12032) 10 months ago
ggml-kompute
llama : add Qwen2VL support + multimodal RoPE (llama/10361) about 1 year ago
ggml-metal
metal : improve FA + improve MoE (llama/12612) 9 months ago
ggml-musa
cuda : enable CUDA Graph on CUDA Toolkit < 12.x (llama/12394) 9 months ago
ggml-opencl
opencl: add multi and vision rope, `gelu_quick` and `im2col` (llama/12600) 9 months ago
ggml-rpc
rpc : send hash when tensor data is above some fixed threshold (llama/12496) 9 months ago
ggml-sycl
files : remove old wkv6 (#0) 9 months ago
ggml-vulkan
metal : improve FA + improve MoE (llama/12612) 9 months ago
CMakeLists.txt

11.4 kB

Fix build on Windows when ccache enabled (ggml/9954) (llama/9976) 9 months ago
ggml-alloc.c

38.5 kB

ggml : upgrade init_tensor API to return a ggml_status (llama/11854) 10 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

17.4 kB

ggml-backend : fix backend search path (llama/12330) 9 months ago
ggml-backend.cpp

77.6 kB

ggml : portability fixes for VS 2017 (llama/12150) 10 months ago
ggml-common.h

133 kB

CUDA: use arch list for compatibility check (llama/11775) 10 months ago
ggml-impl.h

19.2 kB

ggml : sync/merge cmake,riscv,powerpc, add common.cmake (ggml/0) 9 months ago
ggml-opt.cpp

31.7 kB

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

215 kB

ggml : portability fixes for VS 2017 (llama/12150) 10 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

212 kB

metal : improve FA + improve MoE (llama/12612) 9 months ago
gguf.cpp

45 kB

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